© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    references to threats and dangers

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

    "danger" or "dangers"

    np_acts-logits-general · gemini-2.0-flash

    danger and threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.80
     &___
    -0.77
    glMatrixMode
    -0.75
     مرئيه
    -0.72
    harusnya
    -0.72
     ModelExpression
    -0.70
    irmed
    -0.68
     AssemblyCulture
    -0.67
    SBATCH
    -0.67
     AutoMapper
    -0.67
    POSITIVE LOGITS
     danger
    1.33
     threat
    1.23
     threats
    1.17
     dangers
    1.16
     Danger
    1.11
    threat
    1.06
    danger
    1.03
    Danger
    0.98
    Threat
    0.96
     Threat
    0.95
    Activations Density 0.137%

    No Known Activations