© 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. 61572
    Prev
    Next
    INDEX
    Explanations

    patterns of conditional and proportional language in legal or contractual contexts

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

    possessive pronouns like its

    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
    parsedMessage
    -0.76
    AddTagHelper
    -0.73
    contentLoaded
    -0.70
     GenerationType
    -0.68
    sizeCache
    -0.68
    IVEREF
    -0.67
     disambiguazione
    -0.66
    getSystemService
    -0.65
     ujednoznacz
    -0.65
     مشين
    -0.61
    POSITIVE LOGITS
     its
    1.54
    其
    1.03
    its
    0.99
     their
    0.96
    Its
    0.96
     Its
    0.94
     sua
    0.81
     ihrer
    0.80
    它的
    0.79
     seu
    0.76
    Activations Density 0.103%

    No Known Activations