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. 14945
    Prev
    Next
    INDEX
    Explanations

    terms related to health, biology, and specific medical conditions

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

    Follows specific words (life, command, side, duty, cross, amino, blood, order, query)

    np_acts-logits-general · gemini-2.0-flash

    life cycle, command-line, side chains, duty cycle, cross section, amino acids, blood supply, order parameter, query string

    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
     Efq
    -1.04
    İstinadlar
    -0.99
    rawDesc
    -0.98
     themſelves
    -0.88
     Италијани
    -0.85
     intptr
    -0.85
     تضيفلها
    -0.83
    Παραπομπές
    -0.82
     RISERV
    -0.81
     himſelf
    -0.81
    POSITIVE LOGITS
    -
    0.91
     
    0.57
    ‐
    0.51
    -​
    0.50
    ‑
    0.48
    _
    0.45
     […]
    0.45
    -)
    0.44
    Continue
    0.43
    -/
    0.42
    Activations Density 0.960%

    No Known Activations