© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11343
    Prev
    Next
    INDEX
    Explanations

    references to species or medical terms related to cancer treatments or conditions

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

    The token "Sar" and following characters

    np_acts-logits-general · gemini-2.0-flash

    Sar and related words

    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
    حياتها
    -0.68
    antaine
    -0.65
    حياته
    -0.63
     EconPapers
    -0.62
    المكان
    -0.60
     TextInputType
    -0.59
     numberWith
    -0.58
    #
    -0.57
    Externí
    -0.56
    Географиясе
    -0.56
    POSITIVE LOGITS
    Sar
    0.94
     Sar
    0.91
     sar
    0.88
    sar
    0.66
    fillType
    0.59
     Sarasota
    0.57
     Saras
    0.56
     Sarac
    0.53
     للاسماء
    0.52
     SAR
    0.52
    Activations Density 0.095%

    No Known Activations