© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1349
    Prev
    Next
    INDEX
    Explanations

    specific dosages and measurements in a medical context

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

    Values with units, often temperatures or doses

    np_acts-logits-general · gemini-2.0-flash

    units of measurement and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    addContainerGap
    -0.74
    migrationBuilder
    -0.70
    ScopeManager
    -0.67
    səhifə
    -0.66
     queſta
    -0.65
     autorytatywna
    -0.64
    httphttps
    -0.63
    ագրություններ
    -0.63
    iſen
    -0.62
    ftagPool
    -0.62
    POSITIVE LOGITS
     صوتيه
    0.32
    AutoresizingMask
    0.26
    انجليز
    0.23
      
    0.23
    ум
    0.21
    श्चित
    0.21
    -
    0.21
     temp
    0.21
     caisse
    0.21
    ToFit
    0.20
    Activations Density 0.650%

    No Known Activations