© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105758
    Prev
    Next
    INDEX
    Explanations

    code structures and data definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    providedIn
    -0.45
     onPostExecute
    -0.40
    menuStrip
    -0.39
     autorytatywna
    -0.39
     onView
    -0.35
     stir
    -0.34
    urlencoded
    -0.33
     medial
    -0.33
    gravel
    -0.33
     ͡°
    -0.33
    POSITIVE LOGITS
    findpost
    0.62
    kháu
    0.50
    SharedDtor
    0.49
     Signalez
    0.49
    PARATUS
    0.45
    glGen
    0.45
    出版年
    0.44
    ⤹
    0.44
     BoxFit
    0.44
     Größen
    0.44
    Activations Density 0.022%

    No Known Activations