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. 24-GEMMASCOPE-RES-16K
    6. 8298
    Prev
    Next
    INDEX
    Explanations

    details about color specifications and attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Colors

    np_acts-logits-general · gemini-2.0-flash

    dark colors and shades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.61
    awtextra
    -0.58
    ||}
    -0.57
    исленность
    -0.56
    YELLOW
    -0.56
    GraphicsUnit
    -0.54
     białe
    -0.54
     gial
    -0.53
     yellow
    -0.52
     yellows
    -0.52
    POSITIVE LOGITS
     midnight
    0.85
     charcoal
    0.81
     Charcoal
    0.78
     Midnight
    0.75
    Midnight
    0.72
     Graphite
    0.72
    midnight
    0.71
     graphite
    0.69
     chocolate
    0.69
    Grap
    0.69
    Activations Density 0.121%

    No Known Activations