© 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. 9-GEMMASCOPE-RES-131K
    11. 4644
    Prev
    Next
    INDEX
    Explanations

    references to specific data fields or parameters in a programming context

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

    programming fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     missione
    -0.56
     سكانية
    -0.56
     Hugs
    -0.51
     onPostExecute
    -0.51
     Schenk
    -0.50
     רבה
    -0.49
     reputación
    -0.49
     situatie
    -0.49
    ("~/
    -0.49
     Rosales
    -0.49
    POSITIVE LOGITS
    Field
    2.44
     Field
    2.06
     FIELD
    1.47
     Fields
    1.23
    FIELD
    1.14
    DataField
    1.05
    Fields
    1.05
    GetField
    1.03
     Fielding
    1.03
    field
    1.01
    Activations Density 0.010%

    No Known Activations