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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 1917
    Prev
    Next
    INDEX
    Explanations

    functions related to email handling and attachments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.69
     CGPoint
    -0.68
     zelve
    -0.65
     engraçadas
    -0.65
    Spoljašnje
    -0.65
    >>>>>>>
    -0.64
    pausal
    -0.63
    endish
    -0.63
    numerusform
    -0.63
     hoogte
    -0.62
    POSITIVE LOGITS
    <tbody>
    0.64
     sek
    0.61
     Sek
    0.61
     Metabolism
    0.61
     Kur
    0.59
    isti
    0.58
     metabolism
    0.57
    plik
    0.56
    sek
    0.56
    AspNetCore
    0.56
    Activations Density 0.186%

    No Known Activations