© 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. 4-GEMMASCOPE-RES-16K
    11. 1057
    Prev
    Next
    INDEX
    Explanations

    statistical metrics and averages related to patient demographics and clinical measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sooner
    -0.55
    gonia
    -0.48
    ضايا
    -0.47
    heiser
    -0.46
     unbounded
    -0.46
    #![
    -0.44
     الحره
    -0.44
    ❮
    -0.44
     candidates
    -0.43
    candidate
    -0.43
    POSITIVE LOGITS
     average
    1.67
     Average
    1.59
    Average
    1.56
    average
    1.53
     AVERAGE
    1.47
     averages
    1.45
     averaged
    1.43
     averaging
    1.35
    平均
    1.34
     promedio
    1.31
    Activations Density 0.511%

    No Known Activations