© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 28898
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or entities, particularly those starting with "Sh"

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

    words starting with sh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lcccc
    -0.59
    IVersion
    -0.54
    WEBPACK
    -0.47
    %">
    -0.46
    <h3>
    -0.45
     }>
    -0.42
     />;
    -0.41
     כול
    -0.41
     日期
    -0.41
    éez
    -0.41
    POSITIVE LOGITS
     Sh
    2.03
    Sh
    1.88
     sh
    1.59
    sh
    1.29
     SH
    1.20
     Ш
    1.01
     shunt
    0.96
    SH
    0.93
     Shor
    0.91
     Shu
    0.89
    Activations Density 0.012%

    No Known Activations