© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7196
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize intention or concentration on a specific subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 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
    FlatAppearance
    -0.55
    GEBURTSDATUM
    -0.54
     VIDEOTAPE
    -0.51
    -0.49
    bootstrapcdn
    -0.49
     getRule
    -0.48
     enfans
    -0.47
    קישורים
    -0.47
    providedIn
    -0.47
     MotionEvent
    -0.46
    POSITIVE LOGITS
     focus
    1.66
    focus
    1.61
     Focus
    1.49
    Focus
    1.49
     FOCUS
    1.41
    FOCUS
    1.36
     focused
    1.35
     focussed
    1.35
     focuses
    1.33
     Fokus
    1.30
    Activations Density 0.121%

    No Known Activations