© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14314
    Prev
    Next
    INDEX
    Explanations

    questions that initiate inquiries or seek information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whether
    -0.30
     efectivamente
    -0.29
     psychologie
    -0.28
     appré
    -0.28
     liền
    -0.28
     rzeczyw
    -0.26
    样子
    -0.26
     approaches
    -0.26
     actually
    -0.25
     finalement
    -0.25
    POSITIVE LOGITS
    IUrlHelper
    0.73
    MigrationBuilder
    0.71
    
    0.70
    tagHelperRunner
    0.69
    TypedDataSet
    0.67
    AddTagHelper
    0.66
    aarrggbb
    0.65
     CreateTagHelper
    0.65
    uxxxx
    0.65
    AxisAlignment
    0.64
    Activations Density 0.070%

    No Known Activations