© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14357
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to code or programming language syntax

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

    Code snippets containing "+" signs

    np_acts-logits-general · gemini-2.0-flash

    ngx code lines ending with +

    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
    (
    -0.78
    "
    -0.60
    -
    -0.52
    \
    -0.50
    haped
    -0.46
    pixabay
    -0.45
    [
    -0.44
    Auszeichnungen
    -0.44
     nail
    -0.44
    GeneratedCode
    -0.44
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.76
     AssemblyCulture
    0.75
     Réponses
    0.70
    Hentet
    0.68
     kaynağından
    0.68
    पया
    0.66
    })();
    
    0.65
    WebVitals
    0.65
     للاسماء
    0.64
    ImageContext
    0.64
    Activations Density 0.076%

    No Known Activations