© 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. 16-GEMMASCOPE-RES-16K
    11. 9810
    Prev
    Next
    INDEX
    Explanations

    statistical data related to total counts and proportions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.54
    makeConstraints
    -0.53
    intrinsic
    -0.52
    LookAnd
    -0.48
    transQ
    -0.47
    idio
    -0.45
    +#+#
    -0.44
    WithIOException
    -0.44
    cascade
    -0.44
    cresc
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.52
    enderror
    0.40
    eradish
    0.38
    Heute
    0.37
     iniqu
    0.35
    期刊论文
    0.35
     thereof
    0.35
     összes
    0.35
    таратура
    0.34
     today
    0.33
    Activations Density 0.319%

    No Known Activations