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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1021
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to measurements and compositions in experimental procedures

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

    Quantities, proportions, or amounts

    np_acts-logits-general · gemini-2.0-flash

    amounts, quantities, and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.36
     at
    -0.35
    كويكب
    -0.34
     win
    -0.34
    Jäh
    -0.34
    essoal
    -0.32
     in
    -0.30
    Jährige
    -0.30
     :
    -0.29
     свое
    -0.29
    POSITIVE LOGITS
    
    0.69
     CreateTagHelper
    0.68
    SequentialGroup
    0.63
    脚注の使い方
    0.62
    RegressionTest
    0.61
     noDo
    0.60
     Dieſe
    0.59
     zwiſchen
    0.58
    <pad>
    0.58
    [@BOS@]
    0.58
    Activations Density 0.509%

    No Known Activations