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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6160
    Prev
    Next
    INDEX
    Explanations

    items related to practical everyday necessities and specific tools or supplies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.67
    bindParam
    -0.66
    orghini
    -0.62
    BufferException
    -0.61
     صوتيه
    -0.61
     للمعارف
    -0.60
    atillo
    -0.55
     endblock
    -0.55
    Попис
    -0.52
     referenties
    -0.52
    POSITIVE LOGITS
    windowFixed
    0.54
     kits
    0.51
     nécessaire
    0.48
    варь
    0.48
     getItemId
    0.47
    SuspendLayout
    0.47
    følgelig
    0.47
     spare
    0.46
    IsMutable
    0.46
    UpInside
    0.46
    Activations Density 0.254%

    No Known Activations