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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9699
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.77
    CppMethod
    -0.68
    expandindo
    -0.67
     كومونز
    -0.63
     newBuilder
    -0.62
     ligiloj
    -0.61
     Verne
    -0.60
    VersionUID
    -0.60
    astify
    -0.57
     للاسماء
    -0.57
    POSITIVE LOGITS
     data
    2.31
    data
    2.14
     Data
    1.94
     DATA
    1.90
    Data
    1.87
    DATA
    1.82
    データ
    1.58
    setData
    1.51
     setData
    1.50
    getData
    1.49
    Activations Density 0.157%

    No Known Activations