© 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. 28532
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ServiceModel
    -1.51
     تعدى
    -0.69
     Ouv
    -0.44
    Hochspringen
    -0.35
    destroyAll
    -0.35
     incomplète
    -0.32
    uncher
    -0.30
    Revenir
    -0.30
    setupUi
    -0.30
     Begründung
    -0.29
    POSITIVE LOGITS
    Personensuche
    4.22
    SPATH
    2.69
    Hentet
    1.93
    principalTable
    1.48
     HttpNotFound
    1.05
    DropTable
    0.98
    ंदीखरीदारी
    0.91
    SharedCtor
    0.81
    posedge
    0.80
    RTHOOK
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.