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. 10-GEMMASCOPE-RES-16K
    6. 15948
    Prev
    Next
    INDEX
    Explanations

    computer vision programming terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adpleegd
    -0.77
     resourceCulture
    -0.69
     Naples
    -0.68
    ObservableList
    -0.67
     Napoléon
    -0.67
    outState
    -0.67
    DeleteBehavior
    -0.66
    !';
    -0.65
     Salta
    -0.64
     ***!
    -0.63
    POSITIVE LOGITS
     cv
    1.71
    cv
    1.58
     CV
    1.39
    opencv
    1.28
    CV
    1.25
     Cv
    1.21
    Cv
    1.14
     OpenCV
    0.99
    cope
    0.69
    tivitas
    0.66
    Activations Density 0.069%

    No Known Activations