© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 83790
    Prev
    Next
    INDEX
    Explanations

    instances of formal notation and references in written text

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

    comments, later discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     queſta
    -0.59
    RefNanny
    -0.58
    TagMode
    -0.55
    TokenNameLBRACE
    -0.55
     arşivlendi
    -0.53
     Wikimédia
    -0.53
    zzleHttp
    -0.52
     wikipagina
    -0.52
     ligiloj
    -0.52
     IBRARY
    -0.51
    POSITIVE LOGITS
    Réponse
    0.47
    ViewFeatures
    0.35
     vou
    0.33
     נד
    0.32
    Supplemental
    0.31
    Debt
    0.30
    Letter
    0.30
     Савезне
    0.30
     adiv
    0.29
    Routledge
    0.29
    Activations Density 0.002%

    No Known Activations