© 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. 54072
    Prev
    Next
    INDEX
    Explanations

    CSS style attributes

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

    css properties and values

    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
    Referanser
    -0.40
    ⓧ
    -0.34
    obiettivo
    -0.34
    ]=>
    -0.33
     něko
    -0.31
     meille
    -0.31
    principalColumn
    -0.30
     række
    -0.28
     össze
    -0.28
     luzes
    -0.28
    POSITIVE LOGITS
    ItemLayout
    0.65
    gonic
    0.57
    providedIn
    0.55
    Życiorys
    0.54
    AtIndexPath
    0.53
    UnusedPrivate
    0.52
     Bleach
    0.51
    jooq
    0.51
    scrapy
    0.50
    Jereo
    0.50
    Activations Density 0.019%

    No Known Activations