© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues and medical conditions

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    diseases and drugs

    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
    hline
    -0.54
     newBuilder
    -0.54
    FTFY
    -0.53
    enumii
    -0.52
    fähig
    -0.51
    Ծանոթ
    -0.51
    *~*~
    -0.51
     lời
    -0.50
     cistern
    -0.49
    حياته
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.90
    extAlignment
    0.82
    Portale
    0.73
    CodeAttribute
    0.72
    Personensuche
    0.71
    tvguidetime
    0.60
    resizingMask
    0.59
     tartalomajánló
    0.57
    ########.
    0.57
    principalColumn
    0.57
    Activations Density 0.695%

    No Known Activations