© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10640
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to supplementary materials in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.86
    writeFieldEnd
    -0.82
    ]")]
    -0.80
    setVerticalGroup
    -0.69
    %</
    -0.68
    最快更新
    -0.68
    >--}}
    -0.67
     مشين
    -0.67
    !";
    -0.67
     ModelExpression
    -0.66
    POSITIVE LOGITS
    _
    0.69
     supernatant
    0.61
    _.
    0.60
    .
    0.57
     disulfide
    0.51
     FINAL
    0.50
     saar
    0.48
    %
    0.48
    件
    0.48
    index
    0.48
    Activations Density 0.855%

    No Known Activations