© 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. 38-GEMMASCOPE-RES-16K
    11. 8664
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols associated with formal proofs and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.72
    parsedMessage
    -0.69
    Билгалдахарш
    -0.68
     Chwiliwch
    -0.68
    ValueStyle
    -0.68
     disambiguazione
    -0.67
     utafitiHapana
    -0.66
     surla
    -0.66
     ModelExpression
    -0.66
    oa̍t
    -0.66
    POSITIVE LOGITS
    +,
    0.37
    loc
    0.31
    N
    0.29
    i
    0.28
    ind
    0.28
     exceso
    0.28
    F
    0.28
    bare
    0.27
    cano
    0.27
    reg
    0.27
    Activations Density 2.415%

    No Known Activations