© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13436
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and terminology, particularly from computer vision libraries

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

    OpenCV related tokens

    np_acts-logits-general · gemini-2.0-flash

    OpenCV cvtColor Mat CV_BGR2HSV

    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
    saraba
    -0.62
    providedIn
    -0.53
    usertype
    -0.52
    pirable
    -0.51
    omyelitis
    -0.51
     MyBatis
    -0.51
    SEGUIR
    -0.51
    ondheim
    -0.50
    PostExecute
    -0.50
    geable
    -0.50
    POSITIVE LOGITS
     cv
    1.07
    cv
    1.04
     CV
    0.92
    Cv
    0.85
    CV
    0.83
     Cv
    0.82
    Mat
    0.70
     Mat
    0.63
     مشين
    0.55
     Scalar
    0.55
    Activations Density 0.126%

    No Known Activations