© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4786
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and methods

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

    starting with "St" or "al"

    np_acts-logits-general · gemini-2.0-flash

    St words

    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
    stated
    -0.76
    statement
    -0.72
     STAFF
    -0.68
     stated
    -0.68
    staff
    -0.68
     statement
    -0.67
    STAFF
    -0.66
     staff
    -0.65
     Staff
    -0.65
     STATEMENT
    -0.64
    POSITIVE LOGITS
     quo
    0.68
    multer
    0.61
    holders
    0.58
     linkovi
    0.56
     ویکی‌پدیای
    0.56
     Quo
    0.54
     Zjednoc
    0.52
    endous
    0.51
     ویکی‌پدیا
    0.51
    Unmarshaller
    0.51
    Activations Density 0.367%

    No Known Activations