© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    terms related to hypotheses and proposals in research

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

    followed by "size" and "hypothe" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    hypothesize

    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
    onComplete
    -0.55
    tiéndose
    -0.53
    ization
    -0.53
     conversion
    -0.51
    fible
    -0.51
    číta
    -0.50
    onAdd
    -0.50
     extension
    -0.50
     expansion
    -0.50
     division
    -0.50
    POSITIVE LOGITS
    SCRIBE
    0.77
     pubblici
    0.69
    queryInterface
    0.67
    Hentet
    0.66
     popoli
    0.65
    +#+#
    0.62
     âmes
    0.60
    PyExc
    0.60
    seamnă
    0.59
    InjectAttribute
    0.59
    Activations Density 0.445%

    No Known Activations