© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 599
    Prev
    Next
    INDEX
    Explanations

    references to image processing functions and their parameters in OpenCV

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

    Code, programming, and image processing terms

    np_acts-logits-general · gemini-2.0-flash

    cv:: C++ functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.41
     empuj
    -0.40
     Autónoma
    -0.37
     pousse
    -0.35
    DebuggerNonUser
    -0.34
    CodeDom
    -0.34
     everyone
    -0.34
     tetto
    -0.33
     let
    -0.33
     calculer
    -0.33
    POSITIVE LOGITS
    opencv
    0.77
     OpenCV
    0.77
    VideoCapture
    0.76
    imread
    0.63
    awtextra
    0.57
    ThroughAttribute
    0.56
    waitKey
    0.54
    Rüyada
    0.53
     Pistol
    0.51
    CCTV
    0.51
    Activations Density 0.171%

    No Known Activations