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. 21-GEMMASCOPE-RES-16K
    6. 7466
    Prev
    Next
    INDEX
    Explanations

    code structures related to the export of functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    devamını
    -0.49
    /
    -0.48
     Be
    -0.47
     Future
    -0.47
     H
    -0.46
     U
    -0.46
     World
    -0.46
     Ha
    -0.46
     T
    -0.45
    were
    -0.45
    POSITIVE LOGITS
    const
    2.33
     const
    1.94
     constexpr
    1.06
     constriction
    1.05
    let
    1.05
     Const
    1.03
     CONST
    0.95
    Const
    0.95
     readonly
    0.94
    PerformLayout
    0.90
    Activations Density 0.086%

    No Known Activations