© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 88672
    Prev
    Next
    INDEX
    Explanations

    references to Amazon and related product management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Amazon sellers and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ganchillo
    -0.34
     user
    -0.29
     purchase
    -0.29
     basket
    -0.28
    user
    -0.27
     BED
    -0.25
     soci
    -0.25
     godine
    -0.24
    builtins
    -0.24
     collaborateurs
    -0.24
    POSITIVE LOGITS
     betweenstory
    0.96
     Signalez
    0.86
    IntoConstraints
    0.79
    StructEnd
    0.77
    tagHelperRunner
    0.76
     ब्रेकडाउन
    0.75
     GenerationType
    0.75
     Infórmanos
    0.75
    下载附件
    0.73
    CppMethod
    0.71
    Activations Density 0.020%

    No Known Activations