Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5790
    Prev
    Next
    INDEX
    Explanations

    various specific entities and terms related to mythology, biology, and genetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ávajú
    -0.65
     Catto
    -0.61
    crombie
    -0.61
    umą
    -0.60
     Leap
    -0.59
    Sys
    -0.58
     intervening
    -0.57
     souls
    -0.57
    illoma
    -0.57
     McLaugh
    -0.56
    POSITIVE LOGITS
     ویکی‌پدی
    1.00
     ostavi
    0.97
    RenderAtEndOf
    0.93
     Italijani
    0.87
     utafitiHapana
    0.87
     Chwiliwch
    0.86
     للمعارف
    0.83
     समीक्षाओं
    0.83
    Билгалдахарш
    0.80
     vänt
    0.78
    Activations Density 0.629%

    No Known Activations