© 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. 38166
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, terms, or categories

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

    sanitized, defunct, renames, expatriate, funneling

    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
     betweenstory
    -0.68
     Erbe
    -0.62
     waer
    -0.60
     Erben
    -0.60
     InputDecoration
    -0.58
    Története
    -0.56
    parsedMessage
    -0.56
     Schuld
    -0.56
     Raub
    -0.55
     Werden
    -0.52
    POSITIVE LOGITS
     unſ
    0.45
    ləş
    0.39
    ghijklmnop
    0.38
     الإنس
    0.35
    מ
    0.35
     juſ
    0.34
     iſt
    0.34
    neſs
    0.34
    Invo
    0.34
     primary
    0.33
    Activations Density 0.109%

    No Known Activations