© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    objects representing API resource definitions and their roles in code

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

    Comes after ":" or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    character delimited data

    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
     Walters
    -0.42
     was
    -0.41
    +#+#
    -0.41
    Kapcsolódó
    -0.40
     when
    -0.40
     статистики
    -0.40
     also
    -0.39
    Will
    -0.39
     Welfare
    -0.39
    žius
    -0.39
    POSITIVE LOGITS
    InjectAttribute
    0.83
    Personendaten
    0.75
    ├──
    0.73
    rungsseite
    0.68
     समीक्षाओं
    0.66
    évaluateur
    0.66
     виправивши
    0.64
     cherchés
    0.63
    IContainer
    0.62
    SPATH
    0.62
    Activations Density 0.264%

    No Known Activations