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. 195
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences and new sections in the text

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

    segments of text related to focus or concentration.

    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
    Plata
    -0.68
    nb
    -0.67
     Methuen
    -0.66
    nake
    -0.62
    ன்ற
    -0.62
     tubing
    -0.60
    Tub
    -0.57
     Sodom
    -0.57
     Schalke
    -0.57
    꿔
    -0.57
    POSITIVE LOGITS
     focus
    1.81
    FOCUS
    1.80
     Focus
    1.72
     FOCUS
    1.71
     focussed
    1.64
    Focus
    1.63
     focuses
    1.62
     Fokus
    1.60
     focused
    1.57
    focus
    1.57
    Activations Density 0.088%

    No Known Activations