Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10240
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize caution and ensure attention to detail

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

    "sure to"

    np_acts-logits-general · gemini-2.0-flash

    make sure to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.86
    ValueStyle
    -0.84
    LookAnd
    -0.83
     ویکی‌پدی
    -0.81
    MigrationBuilder
    -0.76
    Personensuche
    -0.75
    цездатний
    -0.74
    SharedCtor
    -0.73
     SEDS
    -0.73
    InjectAttribute
    -0.67
    POSITIVE LOGITS
    cerer
    0.54
     sure
    0.51
    footed
    0.51
    ure
    0.48
    vant
    0.48
    urem
    0.48
     to
    0.48
    uret
    0.48
    iello
    0.46
    ATURA
    0.46
    Activations Density 0.063%

    No Known Activations