© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 96052
    Prev
    Next
    INDEX
    Explanations

    keywords related to code generation and potential errors in software management

    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
    OGND
    -0.52
     المعيارى
    -0.48
    providedIn
    -0.43
    ffine
    -0.42
    wandel
    -0.42
    iented
    -0.42
    HasColumnName
    -0.41
    VARIABLE
    -0.40
     муль
    -0.39
     kepad
    -0.39
    POSITIVE LOGITS
     comuniques
    0.43
    Халык
    0.40
     nahilalakip
    0.40
    HasForeignKey
    0.39
     tartalomajánló
    0.38
     PFS
    0.38
     SOF
    0.37
    rungsseite
    0.36
    WriteLiteral
    0.36
    érieur
    0.36
    Activations Density 0.008%

    No Known Activations