© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6196
    Prev
    Next
    INDEX
    Explanations

    identifiers and numerical references in academic or technical writing

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

    Within parenthesis, brackets, or code

    np_acts-logits-general · gemini-2.0-flash

    ) followed by number or letter

    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
     disambiguazione
    -0.88
     NSCoder
    -0.88
    ScopeManager
    -0.85
     Normdatei
    -0.82
     виправивши
    -0.78
     JpaRepository
    -0.77
    帖最后由
    -0.77
    rungsseite
    -0.77
    AutoresizingMask
    -0.76
    interopRequire
    -0.76
    POSITIVE LOGITS
    )(
    0.70
    )
    0.62
    ).
    0.50
    ),
    0.47
    )”.
    0.45
    )".
    0.45
    ):
    0.45
    点此举报
    0.43
    ity
    0.43
    Наводи
    0.43
    Activations Density 1.381%

    No Known Activations