© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 60946
    Prev
    Next
    INDEX
    Explanations

    references to configuration settings and management in a technical context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    domain redirection and aliases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.70
    RenderAtEndOf
    -0.68
    Portály
    -0.58
     GenerationType
    -0.55
    +#+#
    -0.55
    <unused14>
    -0.54
    <unused17>
    -0.54
    <unused8>
    -0.54
    <pad>
    -0.54
    [@BOS@]
    -0.54
    POSITIVE LOGITS
     pointing
    0.79
    指向
    0.77
     redirect
    0.70
     alias
    0.69
     aliases
    0.66
     redirects
    0.65
    redirect
    0.65
     redirection
    0.61
    alias
    0.60
     linking
    0.59
    Activations Density 0.154%

    No Known Activations