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. 10-GEMMASCOPE-RES-16K
    6. 4498
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes related to the appearance and characteristics of objects, particularly in automotive and product contexts

    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
     propOrder
    -0.59
    mette
    -0.54
    actylus
    -0.52
     beban
    -0.51
     veau
    -0.50
     professionnel
    -0.49
    فق
    -0.48
     getItemId
    -0.48
    obio
    -0.48
    ValueStyle
    -0.48
    POSITIVE LOGITS
     BoxDecoration
    0.88
    ReusableCell
    0.73
    skin
    0.72
     typelib
    0.71
     skin
    0.71
    classnames
    0.70
    клопе
    0.64
     hull
    0.63
    RenderAtEndOf
    0.63
    SKIN
    0.59
    Activations Density 0.325%

    No Known Activations