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. 13394
    Prev
    Next
    INDEX
    Explanations

    C++ programming language syntax and standard input/output stream operations

    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
    []=$
    -0.68
     referrerpolicy
    -0.62
     onCreateView
    -0.61
    qtype
    -0.58
    delete
    -0.56
    Tikang
    -0.56
    hold
    -0.55
    free
    -0.53
    MigrationBuilder
    -0.52
    ={}
    -0.51
    POSITIVE LOGITS
     <<
    0.80
     <<<<<<<<<<<<<<
    0.74
     >>
    0.66
    SequentialGroup
    0.64
     GIPHY
    0.64
    <<<<<<<<
    0.63
    <<<<
    0.60
    <<
    0.56
    >>
    0.54
     Vienne
    0.54
    Activations Density 0.057%

    No Known Activations