© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8166
    Prev
    Next
    INDEX
    Explanations

    references to drawing or design elements in a programming context

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

    Tokens after slashes or dashes

    np_acts-logits-general · gemini-2.0-flash

    drawing related words

    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
     otomatig
    -0.64
     épis
    -0.63
     présidenti
    -0.62
     متعلقه
    -0.58
     Hentet
    -0.56
    Erreferentziak
    -0.55
    Enllaces
    -0.54
    addCriterion
    -0.54
    SuccessListener
    -0.52
     fisuras
    -0.52
    POSITIVE LOGITS
    Drawing
    1.11
     drawing
    1.00
     Drawing
    0.99
    drawing
    0.84
     DRAWING
    0.83
    DRAW
    0.81
     drawings
    0.72
     Drew
    0.70
     drew
    0.70
     draws
    0.65
    Activations Density 0.005%

    No Known Activations