© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 66386
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or disbelief

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

    expressing uncertainty or negation

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

    the presence of negation words or negative constructions (e.g., "no", "not", "don't").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Vidite
    -0.43
    +#+#
    -0.40
    
    -0.40
    StoryboardSegue
    -0.39
    :✨
    -0.37
     mxArray
    -0.36
     felb
    -0.36
    InSection
    -0.36
     Obrador
    -0.35
    feinander
    -0.34
    POSITIVE LOGITS
     ویکی‌پدیا
    0.54
    NSIndexPath
    0.50
    Šaltiniai
    0.45
    nee
    0.44
    endforeach
    0.43
    ButterKnife
    0.43
    Printer
    0.43
     analogy
    0.42
    fortable
    0.42
    pony
    0.42
    Activations Density 0.044%

    No Known Activations