© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102781
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    出版年
    -0.55
     tricked
    -0.46
    +#+#
    -0.45
    ßlich
    -0.45
    %"),
    -0.44
     boo
    -0.43
    TagMode
    -0.43
    пня
    -0.43
    :✨
    -0.42
    bootstrapcdn
    -0.42
    POSITIVE LOGITS
    SEVERE
    3.03
    severe
    0.93
    Severe
    0.90
     Severe
    0.84
     severe
    0.81
    printStackTrace
    0.73
    GOTREF
    0.69
     propOrder
    0.65
     severa
    0.59
    VersionUID
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.