© 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. 9-GEMMASCOPE-RES-131K
    6. 45663
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mier
    -0.35
     competição
    -0.33
     ritro
    -0.30
     detención
    -0.30
     scoperta
    -0.30
     Púb
    -0.29
     scheda
    -0.29
     explain
    -0.29
     bast
    -0.29
     rehabilitación
    -0.29
    POSITIVE LOGITS
    color
    1.10
     color
    1.04
    COLOR
    0.93
     getColor
    0.91
     Color
    0.91
     COLOR
    0.90
    Color
    0.87
    colour
    0.85
     setColor
    0.84
    coloring
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.