© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105992
    Prev
    Next
    INDEX
    Explanations

    specific code patterns or keywords related to error handling and memory management in programming

    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
    AsUp
    -0.63
     GenerationType
    -0.60
     ModelRenderer
    -0.57
     CommonModule
    -0.56
     Utf
    -0.56
    ArgumentParser
    -0.55
    onedDateTime
    -0.54
     arşivlendi
    -0.54
    tableFuture
    -0.54
    utives
    -0.53
    POSITIVE LOGITS
     OMITBAD
    0.83
     bestemt
    0.37
    templateUrl
    0.36
    ffilm
    0.35
    værende
    0.34
     виправивши
    0.33
    __':
    0.33
    stående
    0.33
    principalTable
    0.33
     følger
    0.32
    Activations Density 0.000%

    No Known Activations