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. 13-GEMMASCOPE-RES-16K
    6. 79
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to conditions and their classifications

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

    the beginning of text sequences or sections.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inet
    -0.63
    multicolumn
    -0.62
    lccc
    -0.62
     Tsche
    -0.62
    MotionEvent
    -0.61
    grpc
    -0.61
    
    -0.61
    ttino
    -0.60
    дель
    -0.60
     Gers
    -0.60
    POSITIVE LOGITS
    lifies
    0.88
    tening
    0.84
    tened
    0.82
     deepened
    0.82
    ENED
    0.81
     Simplify
    0.81
    Simplify
    0.79
     lightening
    0.77
     stiffened
    0.76
     gild
    0.75
    Activations Density 0.332%

    No Known Activations