© 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. 22-GEMMASCOPE-RES-16K
    11. 3207
    Prev
    Next
    INDEX
    Explanations

    specific mathematical formulations and parameters in statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TimeTo
    -0.35
     CrossRef
    -0.34
    web
    -0.33
     solas
    -0.32
    setBlock
    -0.32
    allax
    -0.32
    Hentet
    -0.32
    把她
    -0.31
    (&:
    -0.30
    structors
    -0.30
    POSITIVE LOGITS
     Infórmanos
    0.72
     forState
    0.65
     certain
    0.63
    antMatchers
    0.57
     each
    0.56
    getOutputStream
    0.55
    AndEndTag
    0.54
     poszczegól
    0.53
     every
    0.53
     CERTAIN
    0.52
    Activations Density 1.517%

    No Known Activations