© 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. 24-GEMMASCOPE-RES-131K
    11. 663
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements typically used in code or markup languages

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

    comment markers and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.14
     propOrder
    -1.03
    featureID
    -0.93
    MigrationBuilder
    -0.90
    bootstrapcdn
    -0.86
    ſcher
    -0.80
     BoxFit
    -0.78
     JpaRepository
    -0.78
    iſen
    -0.77
     оригіналу
    -0.75
    POSITIVE LOGITS
    //
    0.40
    ↵
    0.37
    ,
    0.36
        
    0.36
    ↵↵↵
    0.36
    !
    0.36
    0.35
    <strong>
    0.34
    ↵↵
    0.34
    C
    0.33
    Activations Density 0.013%

    No Known Activations