© 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. 20-GEMMASCOPE-RES-16K
    11. 5793
    Prev
    Next
    INDEX
    Explanations

    words related to prevention and risks

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

    phrases indicating attempts to prevent or avoid potential negative outcomes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     HasFactory
    -0.65
    niająca
    -0.57
    Autoritní
    -0.56
     disambiguazione
    -0.56
    :✨
    -0.56
    AsUp
    -0.56
     الرياضيه
    -0.54
    テンツ
    -0.54
    oa̍t
    -0.54
     PeEnEo
    -0.53
    POSITIVE LOGITS
     loss
    0.54
     losing
    0.50
     risk
    0.50
     lose
    0.48
     Verlust
    0.42
     prevent
    0.42
    loss
    0.41
     دچار
    0.40
     perder
    0.40
     RISK
    0.40
    Activations Density 0.236%

    No Known Activations