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. 16-GEMMASCOPE-RES-16K
    6. 2865
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "das" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    IUrlHelper
    -0.75
    ++];
    -0.71
    posedge
    -0.70
    ++]=
    -0.70
    aarrggbb
    -0.70
    expandindo
    -0.68
     Biôgrafia
    -0.66
    ()?;
    -0.64
    BeginContext
    -0.60
    POSITIVE LOGITS
    ⓧ
    0.73
    gorm
    0.61
    ViewSet
    0.54
    Referanser
    0.53
    wahati
    0.53
     will
    0.53
     noqa
    0.53
    VersionUID
    0.52
    anderen
    0.52
    migrationBuilder
    0.51
    Activations Density 0.121%

    No Known Activations