© 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. 20-GEMMASCOPE-RES-131K
    11. 17077
    Prev
    Next
    INDEX
    Explanations

    conditional statements and assumptions in technical contexts

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

    conditional phrases using if, for, or absent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ň
    -0.34
     seyn
    -0.33
     aprend
    -0.30
    LElement
    -0.30
    AutoModerator
    -0.30
    entyfik
    -0.29
     Италијани
    -0.28
    ParseTree
    -0.28
    はじめに
    -0.28
    ťa
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.79
    XmlAccessType
    0.59
    #
    0.56
    Personendaten
    0.53
    umably
    0.53
    脚注の使い方
    0.52
    RTLU
    0.52
     Autorizaciones
    0.52
    +:+
    0.50
    ⮕
    0.50
    Activations Density 0.217%

    No Known Activations