© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101979
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotation marks in text

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

    Punctuation marks inside quotation marks that terminate a direct quote or dialogue.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    OGND
    -0.73
    CloseOperation
    -0.70
    AccessorTable
    -0.64
     للاسماء
    -0.63
     للمعارف
    -0.60
     disponibilités
    -0.60
    énario
    -0.59
    featureID
    -0.59
    دانشنامهٔ
    -0.58
    ſammen
    -0.57
    POSITIVE LOGITS
    simple
    0.35
    enaus
    0.35
    rschein
    0.33
     Toten
    0.32
     she
    0.32
     schlimm
    0.32
    InputLabel
    0.31
     simple
    0.31
    imgur
    0.30
     Photocase
    0.30
    Activations Density 0.028%

    No Known Activations