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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 5662
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawing or illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoxydable
    -1.03
    enderror
    -0.91
    lepší
    -0.85
    ContentAsync
    -0.85
    ngdoc
    -0.84
    stüt
    -0.83
     /\.(
    -0.82
    XmlAccessorType
    -0.80
    setAccessible
    -0.80
    EndGlobalSection
    -0.80
    POSITIVE LOGITS
     drawn
    1.58
     draw
    1.45
     Draws
    1.43
     draws
    1.42
    Draw
    1.40
     Draw
    1.39
    draw
    1.36
     DRAW
    1.36
     drawing
    1.36
     Drawn
    1.34
    Activations Density 0.047%

    No Known Activations