© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3252
    Prev
    Next
    INDEX
    Explanations

    references to generalized linear models and their related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acronyms and abbreviated technical terms (particularly those consisting of capital letters followed by optional numbers or hyphens).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.47
    ValueStyle
    -0.46
    sizeCache
    -0.44
    
    -0.43
    awtextra
    -0.42
    帖最后由
    -0.42
    RotationOrder
    -0.40
    batore
    -0.40
    writeTo
    -0.39
     Faraday
    -0.38
    POSITIVE LOGITS
     GL
    0.80
     Gl
    0.73
    Gle
    0.70
     Gla
    0.68
     gl
    0.68
     Gle
    0.68
     GLE
    0.65
     GLS
    0.62
    Gla
    0.61
     Glenn
    0.60
    Activations Density 0.160%

    No Known Activations