© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 105230
    Prev
    Next
    INDEX
    Explanations

    references to content types and MIME types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SBATCH
    -0.63
     auroit
    -0.62
     pouvoit
    -0.57
    __":
    -0.57
     feroit
    -0.53
    flashdata
    -0.52
     avoient
    -0.52
     étoit
    -0.52
    ArgumentParser
    -0.51
     LoginComponent
    -0.51
    POSITIVE LOGITS
    contentType
    1.72
     contentType
    1.50
    ContentType
    1.34
    setContentType
    0.98
     Content
    0.63
    getContent
    0.62
    Content
    0.60
     CONTENT
    0.57
    MediaType
    0.57
    CTYPE
    0.57
    Activations Density 0.003%

    No Known Activations