© 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. 16-GEMMASCOPE-RES-16K
    11. 3811
    Prev
    Next
    INDEX
    Explanations

    references to injuries and their consequences

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

    "injury" or its plural form

    np_acts-logits-general · gemini-2.0-flash

    injury and circumstances

    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
    cob
    -0.64
    Externí
    -0.61
    íg
    -0.60
     entire
    -0.58
     Entire
    -0.58
    DIRECTION
    -0.57
    entire
    -0.56
     Collapse
    -0.54
    ότη
    -0.53
    basa
    -0.52
    POSITIVE LOGITS
     injuries
    1.27
     injury
    1.25
     Injuries
    1.19
     Injury
    1.15
     injured
    1.14
    Injury
    1.12
    injury
    1.09
    Injuries
    1.07
     INJ
    1.04
     blessures
    1.02
    Activations Density 0.172%

    No Known Activations