© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5847
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reveal" and its variants, indicating the disclosure of information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.81
     deleteById
    -0.62
    stylers
    -0.59
     arşivlendi
    -0.58
     ivelany
    -0.58
     HasFactory
    -0.57
    Tembelea
    -0.56
    abetes
    -0.56
    oa̍t
    -0.56
    Dante
    -0.55
    POSITIVE LOGITS
     reveal
    3.38
     revealed
    3.14
     reveals
    3.05
     revealing
    3.02
    reveal
    2.98
     Reveal
    2.83
    revealed
    2.70
    Reveal
    2.56
     Reveals
    2.56
     Revealed
    2.50
    Activations Density 0.066%

    No Known Activations