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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 529
    Prev
    Next
    INDEX
    Explanations

    the conclusion or closure in a given context

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

    "<end_of_turn>"

    np_acts-logits-general · gemini-2.0-flash

    Wikipedia pages

    np_acts-logits-general · gemini-2.5-flash-lite

    end-of-turn conversation boundary markers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     and
    -0.63
     or
    -0.60
    }{*}{
    -0.57
    ,
    -0.57
    -
    -0.54
    VIAF
    -0.46
     of
    -0.45
     &
    -0.44
      
    -0.43
     car
    -0.42
    POSITIVE LOGITS
     Wikiseite
    0.69
     disambiguazione
    0.68
    ResumeLayout
    0.63
    bibfield
    0.60
     itſelf
    0.59
     ostavi
    0.58
    pecabe
    0.57
     Audiodateien
    0.56
    endpush
    0.55
    Personensuche
    0.55
    Activations Density 0.806%

    No Known Activations