© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121895
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations or contextual terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    ंदीखरीदारी
    -0.56
     CreateTagHelper
    -0.51
    ucket
    -0.48
    +:+
    -0.48
    әрмәләр
    -0.48
    WireFormatLite
    -0.46
    endwhile
    -0.46
     vaikka
    -0.45
     <<<<<<<<<<<<<<
    -0.45
     typelib
    -0.45
    POSITIVE LOGITS
    izielle
    0.35
    MigrationBuilder
    0.34
    stination
    0.34
    RuleContext
    0.33
    的技术
    0.31
    contentInset
    0.30
    ISupport
    0.30
    uchtung
    0.30
    ists
    0.30
    кобрита
    0.29
    Activations Density 0.090%

    No Known Activations