© 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. 105709
    Prev
    Next
    INDEX
    Explanations

    keywords associated with SQL statements and expressions in programming contexts

    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
     Reichen
    -0.57
     Sutherland
    -0.54
     bag
    -0.53
    subpackage
    -0.53
     Nicholson
    -0.52
    Initializable
    -0.51
     Unger
    -0.51
    bag
    -0.50
     MacKenzie
    -0.50
    information
    -0.50
    POSITIVE LOGITS
    stmt
    0.98
     stmt
    0.88
    Stmt
    0.64
     Juillet
    0.58
     Entomol
    0.57
    tgt
    0.54
     Biotechnol
    0.54
     Expr
    0.54
     Mfg
    0.50
     Inorg
    0.50
    Activations Density 0.006%

    No Known Activations