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. 10742
    Prev
    Next
    INDEX
    Explanations

    references to physical interactions and placements involving objects or entities within a defined space

    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
    PreExecute
    -0.75
    ardrop
    -0.68
    abetes
    -0.64
     MainAxisSize
    -0.60
    ğinde
    -0.60
    rítica
    -0.59
    dymyr
    -0.57
    FREQUENCY
    -0.56
     <=",
    -0.56
    JspWriter
    -0.56
    POSITIVE LOGITS
    GenerationType
    0.59
     StatelessWidget
    0.55
    GeneratedCode
    0.54
     GenerationType
    0.48
    ním
    0.46
     상세
    0.45
     تضيفلها
    0.45
    NameInMap
    0.45
    FunctionFlags
    0.44
    unches
    0.44
    Activations Density 0.352%

    No Known Activations