© 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. 7008
    Prev
    Next
    INDEX
    Explanations

    topics related to fashion and the patterns associated with it

    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
    majánló
    -0.65
    canestro
    -0.59
     فريبيس
    -0.58
    ftant
    -0.58
    ніципа
    -0.56
     estadounid
    -0.54
    Personensuche
    -0.53
    linawan
    -0.52
     vooz
    -0.52
    ſcher
    -0.52
    POSITIVE LOGITS
     muß
    0.46
     skall
    0.43
     prestations
    0.41
    ImageContext
    0.40
     httpClient
    0.39
    ercizio
    0.38
    strncmp
    0.36
     _("
    0.36
     problemen
    0.36
    LikeLiked
    0.36
    Activations Density 1.484%

    No Known Activations