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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 15363
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to properties and conditions of mathematical objects

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

    Following "for" and similar words

    np_acts-logits-general · gemini-2.0-flash

    for any and all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.61
    Portale
    -0.61
     OFDb
    -0.59
     kasarigan
    -0.58
    Manbalar
    -0.58
     disambiguazione
    -0.52
    PropertyChanging
    -0.52
    OGND
    -0.50
    digarh
    -0.49
    !*\
    -0.48
    POSITIVE LOGITS
     every
    2.32
     everyone
    2.20
     everything
    2.19
    EVERY
    2.18
     EVERY
    2.13
    everything
    2.08
     everybody
    2.07
    every
    2.06
    everyone
    2.04
     EVERYTHING
    2.00
    Activations Density 1.149%

    No Known Activations