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. 6-GEMMASCOPE-RES-16K
    6. 5217
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to measurements and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.65
    Ссылки
    -0.58
    haften
    -0.53
     للمعارف
    -0.53
    addCriterion
    -0.50
    ViewFeatures
    -0.50
    厘米
    -0.48
     ویکی‌پدیای
    -0.48
    ện
    -0.48
    帖最后由
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
     invokingState
    0.74
     hashCode
    0.74
     ProtoMessage
    0.69
    gridx
    0.69
     NKC
    0.65
    ậc
    0.64
    requestCode
    0.62
    WireFormatLite
    0.62
    HashCode
    0.61
    Activations Density 1.092%

    No Known Activations