Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3417
    Prev
    Next
    INDEX
    Explanations

    instances of medical treatment involving injuries and their severity

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

    injuries or wounds

    np_acts-logits-general · gemini-2.0-flash

    wounds and injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.56
     eingestellt
    -0.51
     Antiquities
    -0.48
     concorda
    -0.45
    حف
    -0.45
    fazione
    -0.43
     cementerio
    -0.43
     îna
    -0.42
    pcm
    -0.42
    권
    -0.42
    POSITIVE LOGITS
     injuries
    1.51
     wounds
    1.45
     injury
    1.40
     Injuries
    1.27
     injured
    1.24
     Injury
    1.21
     wound
    1.21
     lacer
    1.20
     Wounds
    1.19
    Injuries
    1.17
    Activations Density 0.492%

    No Known Activations