© 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. 53203
    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
     esternos
    -0.47
     незавершена
    -0.46
    adpleegd
    -0.46
    تقاوى
    -0.46
    UrlResolution
    -0.43
    Aiheesta
    -0.40
     يتيمه
    -0.39
     engraçadas
    -0.38
    UpInside
    -0.38
    səhifə
    -0.37
    POSITIVE LOGITS
     Schema
    1.09
    Schema
    0.83
     schema
    0.77
    schema
    0.72
    SCHEMA
    0.60
     initComponents
    0.59
    CreateMap
    0.59
    setVerticalGroup
    0.58
     schemas
    0.57
    awtextra
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.