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

    Neuronpedia

    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. 9043
    Prev
    Next
    INDEX
    Explanations

    structures and functions related to programming or scripting, particularly in the context of handling errors and subscriptions

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

    Code related to subscriptions

    np_acts-logits-general · gemini-2.0-flash

    run_subscription activation

    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
     just
    -0.58
     even
    -0.54
     he
    -0.50
    </b>
    -0.47
    ”、“
    -0.45
     of
    -0.44
    No
    -0.43
    ","
    -0.43
     .
    -0.43
    тиков
    -0.42
    POSITIVE LOGITS
    _
    1.70
    \_
    1.15
    IsMutable
    0.94
     متعلقه
    0.92
    mybatisplus
    0.88
    _{-}
    0.86
    IntoConstraints
    0.85
    ſelf
    0.84
    neſs
    0.81
    _-_
    0.79
    Activations Density 1.325%

    No Known Activations