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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21660
    Prev
    Next
    INDEX
    Explanations

    language related to legal agreements and obligations

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

    agreement parties

    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
    WebElementEntity
    -0.49
    UnusedPrivate
    -0.40
     '{@
    -0.38
    postsleuth
    -0.32
    ushu
    -0.32
    داران
    -0.31
    TagHelper
    -0.31
    logen
    -0.31
    tellungs
    -0.31
    pace
    -0.31
    POSITIVE LOGITS
     parties
    2.56
    parties
    2.17
     Parties
    2.16
    Parties
    2.11
     party
    1.99
     PARTIES
    1.89
    party
    1.70
     Parteien
    1.66
    Party
    1.58
     Party
    1.55
    Activations Density 0.314%

    No Known Activations