© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2761
    Prev
    Next
    INDEX
    Explanations

    HTML elements or div tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.98
    oa̍t
    -0.83
     resourceCulture
    -0.79
    Sucesor
    -0.74
    TProtocol
    -0.72
    Geplaatst
    -0.71
    LError
    -0.71
    Rhestr
    -0.70
     doméstica
    -0.70
     bağlantılar
    -0.69
    POSITIVE LOGITS
    div
    1.69
     div
    1.27
     Div
    1.06
    Div
    0.93
    DIV
    0.79
     DIV
    0.73
    olol
    0.63
    aville
    0.62
     divi
    0.61
    )_/¯
    0.59
    Activations Density 0.016%

    No Known Activations