© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7592
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "av" and its variations, suggesting a focus on expressions of possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaſon
    -0.80
    יצוני
    -0.80
     itſelf
    -0.80
     समीक्षाओं
    -0.80
     ſche
    -0.79
     himſelf
    -0.78
     myſelf
    -0.77
     ſtill
    -0.76
     quæ
    -0.76
    Demografía
    -0.75
    POSITIVE LOGITS
     OF
    0.83
     de
    0.83
     of
    0.77
     από
    0.76
     af
    0.72
     của
    0.68
     dari
    0.67
     Of
    0.67
     με
    0.66
     av
    0.65
    Activations Density 0.049%

    No Known Activations