© 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. 101736
    Prev
    Next
    INDEX
    Explanations

    words that denote existence or affirmation in a narrative context

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

    Paragraph boundary markers that indicate transitions between narrative sections or speakers in text.

    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
    tvguidetime
    -0.59
    انتهای
    -0.52
     Roskov
    -0.50
    Spoljašnje
    -0.50
    windowFixed
    -0.50
    Abit
    -0.48
    cussed
    -0.47
    |};
    -0.46
    NewRow
    -0.46
    原始内容存档于
    -0.45
    POSITIVE LOGITS
     initComponents
    0.36
    OCCURRED
    0.32
    WebMethod
    0.31
    ìm
    0.31
    Amicalement
    0.30
     vorg
    0.30
     eff
    0.29
     Advance
    0.29
     notific
    0.29
     advance
    0.29
    Activations Density 0.001%

    No Known Activations