© 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. 23-GEMMASCOPE-RES-16K
    11. 6287
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation related to probabilities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ngdoc
    -0.58
    pail
    -0.56
    moveToFirst
    -0.55
     Arag
    -0.54
     bord
    -0.53
     fiss
    -0.51
    ]=="
    -0.49
    gola
    -0.49
    oplastic
    -0.48
    enskap
    -0.47
    POSITIVE LOGITS
    <sup>
    0.77
     ${
    0.63
    (${
    0.60
    ^{\
    0.60
     }^{\
    0.60
    )^{\
    0.59
     $^{\
    0.59
     ^{\
    0.57
    <sub>
    0.56
    $^{\
    0.54
    Activations Density 0.402%

    No Known Activations