© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    references to audio and translation services in media contexts

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

    Accessibility features (captions, subtitles, braille, interpreting)

    np_acts-logits-general · gemini-2.0-flash

    sign language and interpretation

    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
     pylori
    -0.57
    цездатний
    -0.56
    //
    -0.55
     anticor
    -0.53
     userSchema
    -0.52
     duffel
    -0.52
     ejus
    -0.51
     Leaks
    -0.51
    multer
    -0.51
     McE
    -0.50
    POSITIVE LOGITS
     sign
    1.20
     Sign
    1.16
     deaf
    1.09
     interpreting
    1.06
    Sign
    1.06
     interpreter
    0.99
     interpreters
    0.98
     SIGN
    0.98
     Deaf
    0.94
     signing
    0.93
    Activations Density 0.161%

    No Known Activations