© 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. 97219
    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
    consulté
    -1.02
     незавершена
    -0.88
     ExecuteAsync
    -0.75
     стаття
    -0.53
     protoimpl
    -0.50
    AddTagHelper
    -0.48
    MigrationBuilder
    -0.47
    LayoutStyle
    -0.47
    Comté
    -0.45
    amsmath
    -0.44
    POSITIVE LOGITS
     consultato
    2.77
    protoimpl
    2.63
    archiviato
    1.19
     NSFW
    0.61
    原始内容存档于
    0.57
     تعدى
    0.56
    خصة
    0.52
     useState
    0.44
    migrationBuilder
    0.43
     مرئيه
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.