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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7305
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomical structures and surgical procedures in the context of medical imaging

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

    Ankle and foot anatomy/fractures

    np_acts-logits-general · gemini-2.0-flash

    ankle and elbow anatomy, injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.72
     Réponses
    -0.71
     Reverso
    -0.67
    AutoScaleMode
    -0.67
     azo
    -0.64
     ContentValues
    -0.58
    parsedMessage
    -0.56
    OGND
    -0.55
     coar
    -0.55
     toothpaste
    -0.54
    POSITIVE LOGITS
     inferior
    0.63
     inferiores
    0.59
     hoogte
    0.59
    inferior
    0.57
     superiores
    0.56
    altezza
    0.56
    endregion
    0.54
     laterales
    0.54
     superior
    0.54
     anteriores
    0.53
    Activations Density 0.680%

    No Known Activations