Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15028
    Prev
    Next
    INDEX
    Explanations

    words related to strategies and approaches to various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kollu
    -0.72
     décédé
    -0.70
     poorest
    -0.66
     saddest
    -0.64
     climatisation
    -0.62
     laſt
    -0.61
     pauvre
    -0.61
     heure
    -0.61
     autorité
    -0.61
     brightest
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.71
    __':
    
    0.66
    typeorm
    0.65
    __":
    
    0.64
    yargs
    0.64
    DataAnnotations
    0.62
    MigrationBuilder
    0.61
    makeText
    0.60
    Hozzáférés
    0.58
    tagext
    0.58
    Activations Density 2.198%

    No Known Activations