© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1972
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and amounts

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

    Numeric values associated with options or groups

    np_acts-logits-general · gemini-2.0-flash

    numbers following list items

    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
    Rüyada
    -0.54
    Portail
    -0.50
    IsMutable
    -0.50
     domestiques
    -0.45
     Medusa
    -0.45
    consulté
    -0.45
     '\\;'
    -0.44
    Cyfeiriadau
    -0.43
    prepareStatement
    -0.41
    renderItem
    -0.41
    POSITIVE LOGITS
     Five
    2.01
     Seven
    1.97
     Eight
    1.97
    Five
    1.96
     Six
    1.95
    Seven
    1.93
    Six
    1.91
     Four
    1.91
     Three
    1.90
    Four
    1.89
    Activations Density 0.279%

    No Known Activations