© 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. 22-GEMMASCOPE-RES-16K
    11. 8287
    Prev
    Next
    INDEX
    Explanations

    references to original sources or structures in a document

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

    "original" or tokens appearing with "original"

    np_acts-logits-general · gemini-2.0-flash

    original

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -1.20
     autorytatywna
    -1.03
     الرياضيه
    -0.87
    setVerticalGroup
    -0.85
     propOrder
    -0.83
    abestanden
    -0.79
    complexContent
    -0.79
    ftagPool
    -0.76
     فريبيس
    -0.73
     Roskov
    -0.73
    POSITIVE LOGITS
     original
    3.77
    original
    3.39
    Original
    3.05
     Original
    2.91
     ORIGINAL
    2.80
     originals
    2.72
     originales
    2.68
    ORIGINAL
    2.63
     originale
    2.61
     originally
    2.61
    Activations Density 0.673%

    No Known Activations