© 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. 18-GEMMASCOPE-RES-16K
    6. 6568
    Prev
    Next
    INDEX
    Explanations

    import statements and event handling in Java GUI programming

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

    "awt" or "AW" or "aw"

    np_acts-logits-general · gemini-2.0-flash

    awt, aws context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.71
    thenReturn
    -0.71
    ergies
    -0.67
    MultipartFile
    -0.59
     serre
    -0.58
     genommen
    -0.56
    sonaro
    -0.55
    ніципалі
    -0.55
    erweise
    -0.54
    yards
    -0.54
    POSITIVE LOGITS
    awt
    2.07
    AutoScaleMode
    0.84
    ImageContext
    0.78
    uxxxx
    0.68
    HandlerContext
    0.65
    Awkward
    0.64
    swt
    0.61
     aw
    0.60
    Helvetica
    0.60
    baud
    0.57
    Activations Density 0.007%

    No Known Activations