© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1188
    Prev
    Next
    INDEX
    Explanations

    mentions of the CUDA and GTK frameworks in the context of programming

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

    GUI library abbreviations

    np_acts-logits-general · gemini-2.0-flash

    C++ multi-library code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.93
    település
    -0.80
    ControllerAdvice
    -0.78
    elemField
    -0.75
    prefixer
    -0.73
    TemporalType
    -0.73
    ViewImports
    -0.73
     Baillargeon
    -0.72
    ISupport
    -0.69
     שוליים
    -0.69
    POSITIVE LOGITS
     Diſ
    0.60
    ơi
    0.51
     Reſ
    0.49
     ciga
    0.49
     Adven
    0.48
     epile
    0.47
     jsPsych
    0.47
     Damas
    0.47
    diciones
    0.45
     echi
    0.45
    Activations Density 0.331%

    No Known Activations