© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 99585
    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
    TABLES
    -0.39
     Wydawnictwo
    -0.38
    tables
    -0.37
     buoni
    -0.37
     little
    -0.35
     marrone
    -0.35
     ricor
    -0.35
    Union
    -0.34
     Jungen
    -0.34
    hips
    -0.34
    POSITIVE LOGITS
    openqa
    3.69
    WebElementEntity
    1.10
    UserScript
    1.08
    rungsseite
    1.00
     EconPapers
    0.88
    httphttps
    0.82
    adaptiveStyles
    0.81
     linkovi
    0.80
     Италијани
    0.78
     gynhyrchwyd
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.