© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and responses in a narrative context

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

    answers and replies

    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
    bolista
    -0.36
    GraphicsUnit
    -0.34
    цездатний
    -0.33
     gegen
    -0.32
     ModelExpression
    -0.31
    ImageContext
    -0.31
    UAWEI
    -0.31
    ∬
    -0.31
    liferay
    -0.31
     CreateTagHelper
    -0.30
    POSITIVE LOGITS
     answer
    2.91
     answers
    2.69
     answered
    2.42
     reply
    2.38
     Antwort
    2.34
     Answer
    2.33
    answer
    2.31
     réponse
    2.28
     replies
    2.27
     risposta
    2.27
    Activations Density 0.523%

    No Known Activations