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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7344
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions primarily from the OpenCV library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteLiteral
    -0.68
     napraw
    -0.67
     Bonif
    -0.65
    adpleegd
    -0.65
     Warsaw
    -0.64
    APORE
    -0.64
     schia
    -0.64
    udahkan
    -0.62
     Beton
    -0.61
     Tark
    -0.61
    POSITIVE LOGITS
     cv
    2.71
    cv
    2.65
     CV
    2.27
    CV
    2.12
    Cv
    1.83
     Cv
    1.79
    opencv
    1.33
     OpenCV
    1.09
    cvs
    0.93
     Vitae
    0.85
    Activations Density 0.077%

    No Known Activations