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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11224
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to motions and judgments in court cases

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

    legal outcomes and decisions (granted, denied, approved, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IBAction
    -0.45
     useEffect
    -0.35
    GetAsync
    -0.33
    ambiguation
    -0.30
    WriteString
    -0.29
     sprintf
    -0.29
     vol
    -0.29
    bindValue
    -0.29
    tituzione
    -0.29
     linkovi
    -0.28
    POSITIVE LOGITS
     approved
    2.13
     approval
    2.09
     approve
    1.97
     Approval
    1.88
     Approved
    1.82
     approvals
    1.77
    approved
    1.74
     APPROVAL
    1.73
     approving
    1.73
     approves
    1.71
    Activations Density 0.999%

    No Known Activations