Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 5147
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The main thing this neuron does is find the digit "0" and, to a lesser extent, the digit "5" within numerical sequences.

    oai_token-act-pair · gemini-2.5-flashTriggered by @arielgoldsteinlab

    numerical values with decimal points or percentages.

    oai_token-act-pair · deepseek-r1Triggered by @arielgoldsteinlab

    numbers and numerical values embedded in text.

    oai_token-act-pair · deepseek-v3Triggered by @arielgoldsteinlab

    say numbers/Math formulas

    np_max-act-logits · deepseek-v3Triggered by @arielgoldsteinlab

    numbers

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab

    numerical expressions featuring the digit 5, especially round figures with trailing zeros or .5 values (percentages, currencies, measurements).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.15
    OGND
    -0.85
     womb
    -0.84
    CrossRef
    -0.83
    theless
    -0.81
    ❋
    -0.80
     Ecc
    -0.79
    ={({
    -0.78
    ίνη
    -0.77
     scones
    -0.77
    POSITIVE LOGITS
    #+#
    0.69
     StringUtil
    0.62
    zugehen
    0.60
     Purdy
    0.59
     LSB
    0.59
     fifty
    0.58
     mList
    0.58
     CSP
    0.58
    dersfield
    0.58
     PIL
    0.57
    Activations Density 0.313%

    No Known Activations