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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11468
    Prev
    Next
    INDEX
    Explanations

    variations of the word "sho" and its derivatives 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 @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autos
    -0.41
     meres
    -0.41
    localctx
    -0.40
    ClassId
    -0.38
    Espèce
    -0.38
    CppMethod
    -0.36
    VolleyError
    -0.36
     pageNo
    -0.35
    ussis
    -0.35
    setAuto
    -0.35
    POSITIVE LOGITS
    Sho
    0.86
     Sho
    0.84
    sho
    0.74
     sho
    0.74
     SHO
    0.62
     SHOCK
    0.57
    SHOP
    0.57
     SHOP
    0.56
     ショ
    0.53
    Shock
    0.52
    Activations Density 0.129%

    No Known Activations