© 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. 9019
    Prev
    Next
    INDEX
    Explanations

    specific terms and data related to laws or legal proceedings

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

    after single letters

    np_acts-logits-general · gemini-2.0-flash

    Lévy, Lind, Miss, demonstrations, All

    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
    encils
    -0.83
    othesis
    -0.78
    BibitemShut
    -0.76
    pecially
    -0.76
    oforte
    -0.74
    sterious
    -0.72
    nastics
    -0.71
    mallows
    -0.71
    học
    -0.70
    ratulations
    -0.70
    POSITIVE LOGITS
    ley
    0.75
    l
    0.67
    ham
    0.66
    man
    0.66
    lan
    0.62
    ak
    0.62
    uz
    0.61
    well
    0.60
    ik
    0.60
    van
    0.59
    Activations Density 0.839%

    No Known Activations