© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83299
    Prev
    Next
    INDEX
    Explanations

    elements related to discussions about professionalism and qualifications in a work or legal context

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

    sex, gender, or race biased explanations

    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
     EconPapers
    -1.09
     Roskov
    -0.88
    majánló
    -0.85
    ロウィン
    -0.81
     propOrder
    -0.81
    <unused79>
    -0.78
    [@BOS@]
    -0.78
    <unused23>
    -0.78
    <pad>
    -0.77
    <unused3>
    -0.77
    POSITIVE LOGITS
    ‐
    0.32
    ‑
    0.30
     described
    0.24
     {?
    0.23
    P
    0.23
     ayer
    0.22
    —
    0.22
     [
    0.22
    –
    0.22
    var
    0.21
    Activations Density 0.051%

    No Known Activations