© 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. 16368
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords and terms

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

    Prefixes (bat, trans, multi, min, con, mer, ad, ho, au, ex)

    np_acts-logits-general · gemini-2.0-flash

    word beginnings

    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
    NewUrlParser
    -1.06
    giène
    -0.77
    écution
    -0.68
    __*/
    -0.68
     []:
    -0.64
    ambiguation
    -0.63
    чало
    -0.62
     Audiodateien
    -0.61
    firmasi
    -0.59
    $_['
    -0.59
    POSITIVE LOGITS
    aimana
    0.67
     GIPHY
    0.58
    Хро
    0.56
     elétrica
    0.56
    resizingMask
    0.56
     acrylique
    0.55
    etheless
    0.55
    sterious
    0.55
     ویکی‌پدی
    0.54
    SupportActionBar
    0.54
    Activations Density 0.679%

    No Known Activations