© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 123214
    Prev
    Next
    INDEX
    Explanations

    references to social hierarchy and structural roles within society

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

    health and biology topics

    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
    -0.52
    URLException
    -0.47
    quiv
    -0.40
    itoare
    -0.39
     lazy
    -0.39
    枕
    -0.39
     hinweg
    -0.38
     Equatorial
    -0.38
     iridescent
    -0.37
    Jeografia
    -0.37
    POSITIVE LOGITS
    }`;
    0.38
     comté
    0.38
     OMITBAD
    0.38
     Dân
    0.38
    例文帳に追加
    0.37
     ElementRef
    0.37
     Италијани
    0.36
    Спољашње
    0.36
     uParam
    0.36
    IntoConstraints
    0.36
    Activations Density 0.074%

    No Known Activations