© 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. 10560
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand or product name related to footwear

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

    Characters, punctuation, and bracketed words

    np_acts-logits-general · gemini-2.0-flash

    supra shoes

    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
    iffion
    -0.81
    ſtanding
    -0.79
     Efq
    -0.76
    resaid
    -0.76
    InputBorder
    -0.75
     myſelf
    -0.74
    BibitemShut
    -0.74
    leſs
    -0.73
    ſhip
    -0.72
    pecially
    -0.71
    POSITIVE LOGITS
    e
    0.94
    s
    0.93
    t
    0.76
    d
    0.75
    n
    0.75
    o
    0.74
    ing
    0.72
    r
    0.71
    er
    0.70
    y
    0.70
    Activations Density 0.362%

    No Known Activations