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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9482
    Prev
    Next
    INDEX
    Explanations

    conditional statements and branching logic in code

    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
    niksi
    -0.51
    دار
    -0.47
    roj
    -0.46
    urgo
    -0.45
     parfüm
    -0.45
     multa
    -0.45
    Bar
    -0.45
    ALLOW
    -0.44
    RowCount
    -0.44
    baran
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.89
     للمعارف
    0.85
    /*
    0.84
    writeFieldEnd
    0.82
    +#+#
    0.77
    //
    0.76
    ########.
    0.76
    Vidite
    0.76
     समीक्षाओं
    0.76
    sidemargin
    0.76
    Activations Density 0.019%

    No Known Activations