Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 16065
    Prev
    Next
    INDEX
    Explanations

    mentions of "fe" as a prefix in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.75
     Basta
    -0.63
     autorytatywna
    -0.63
     kasarigan
    -0.61
    parsedMessage
    -0.60
    сылкі
    -0.58
    WriteLiteral
    -0.56
    govine
    -0.56
    zheimer
    -0.55
    RenderAtEndOf
    -0.55
    POSITIVE LOGITS
    Fe
    1.08
     Fe
    1.07
     fe
    0.97
     FE
    0.90
    FE
    0.83
     Felicia
    0.80
    fe
    0.77
    fees
    0.76
     fee
    0.73
     Fee
    0.73
    Activations Density 0.125%

    No Known Activations