© 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. 21-GEMMASCOPE-RES-16K
    11. 13051
    Prev
    Next
    INDEX
    Explanations

    details about injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.57
    pcm
    -0.51
    </tfoot>
    -0.45
    
    -0.43
    adaptador
    -0.42
     Doppel
    -0.42
     Antiquities
    -0.42
    thâu
    -0.41
    Doppel
    -0.41
     Lös
    -0.41
    POSITIVE LOGITS
     injuries
    2.25
     injury
    2.11
     Injuries
    1.90
     injured
    1.87
     wounds
    1.84
     Injury
    1.83
    injury
    1.74
    Injuries
    1.73
     injure
    1.70
    Injury
    1.68
    Activations Density 0.441%

    No Known Activations