© 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. 9-GEMMASCOPE-RES-131K
    11. 61591
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation marks, indicating connections and relationships in sentences

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

    HTML tags like `<br>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.66
    InputBorder
    -0.60
    WillAppear
    -0.60
    GTCX
    -0.59
    AnchorStyles
    -0.58
    脚注の使い方
    -0.55
    principalColumn
    -0.54
    RTSC
    -0.54
    ViewFeatures
    -0.54
    oredCriteria
    -0.54
    POSITIVE LOGITS
     meille
    0.45
     appartient
    0.40
     cũ
    0.40
     appartiennent
    0.39
     belongs
    0.39
     mijne
    0.39
     bukanlah
    0.39
     comigo
    0.39
    이고
    0.37
     kepad
    0.36
    Activations Density 0.301%

    No Known Activations