© 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. 7938
    Prev
    Next
    INDEX
    Explanations

    variable assignments and definitions, particularly in programming code

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

    Followed by 'pt' and a method call

    np_acts-logits-general · gemini-2.0-flash

    pt.get("tuning

    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
    gpl
    -0.50
     كورة
    -0.48
    ytu
    -0.46
    zeptember
    -0.45
    Pranala
    -0.45
    occuper
    -0.45
    faring
    -0.44
    ći
    -0.44
    ándor
    -0.43
     suya
    -0.42
    POSITIVE LOGITS
    RegistryLite
    0.77
    qrstuvwxyz
    0.73
    InjectAttribute
    0.72
    AddTagHelper
    0.71
    FOOTNOTES
    0.68
     ModelExpression
    0.66
     AspNetCore
    0.65
    InputBorder
    0.64
    //
    0.62
    DoubleQuotes
    0.61
    Activations Density 0.150%

    No Known Activations