© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15996
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions and database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.66
     '\\;'
    -0.57
     ModelExpression
    -0.54
     informée
    -0.50
     Sucher
    -0.48
     esternos
    -0.48
    ChromeDriver
    -0.47
    leuth
    -0.47
    ChildScrollView
    -0.46
    dataclass
    -0.46
    POSITIVE LOGITS
    Migrations
    0.74
    migrationBuilder
    0.67
     migrations
    0.65
     migration
    0.63
    OpenHelper
    0.55
     Migration
    0.54
    Migration
    0.54
    migrations
    0.50
    migration
    0.50
     mig
    0.49
    Activations Density 0.120%

    No Known Activations