© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 8914
    Prev
    Next
    INDEX
    Explanations

    terms related to threats and risks, particularly in health contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    setVerticalGroup
    -0.52
     ErrIntOverflow
    -0.46
     للاسماء
    -0.42
    Debugging
    -0.36
    .*")]
    -0.36
     debugging
    -0.35
     EconPapers
    -0.35
    ❋
    -0.35
    GOTREF
    -0.34
     betweenstory
    -0.34
    POSITIVE LOGITS
     threat
    2.95
     threats
    2.72
    threat
    2.64
     threatening
    2.58
     Threat
    2.55
     threaten
    2.55
    Threat
    2.50
     threatens
    2.41
     threatened
    2.41
     danger
    2.36
    Activations Density 0.870%

    No Known Activations