© 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. 62250
    Prev
    Next
    INDEX
    Explanations

    legal motions and requests related to court judgments and appeals

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

    motion to act

    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
     ste
    -0.35
    ffic
    -0.33
    й
    -0.33
    要
    -0.32
     highly
    -0.32
    所
    -0.32
     sat
    -0.31
     Semi
    -0.31
     ADV
    -0.30
    net
    -0.30
    POSITIVE LOGITS
    RegressionTest
    0.75
    tagHelperRunner
    0.72
    featureID
    0.71
     hırka
    0.70
     InputDecoration
    0.70
     الحره
    0.69
    uxxxx
    0.68
     reconsideration
    0.68
     للمعارف
    0.66
    InjectAttribute
    0.65
    Activations Density 0.428%

    No Known Activations