© 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. 104742
    Prev
    Next
    INDEX
    Explanations

    frequent references to utility or practicality

    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
     betweenstory
    -0.60
    PRNewswire
    -0.55
    Rhestr
    -0.51
    WriteBarrier
    -0.51
     cjs
    -0.50
    retum
    -0.49
    akaian
    -0.47
    ereum
    -0.47
    migrationBuilder
    -0.46
    principalColumn
    -0.46
    POSITIVE LOGITS
     Handy
    1.21
    Handy
    1.14
    handy
    1.13
     handy
    1.08
     dandy
    0.84
    hand
    0.68
     Hand
    0.67
     Dandy
    0.67
     hand
    0.65
     HAND
    0.65
    Activations Density 0.003%

    No Known Activations