© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11506
    Prev
    Next
    INDEX
    Explanations

    references to input and output parameters in programming contexts

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

    "input" and related terms

    np_acts-logits-general · gemini-2.0-flash

    input and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.87
     HasFactory
    -0.75
     initComponents
    -0.72
     joaat
    -0.69
    enumi
    -0.67
    RTLD
    -0.66
    QtWidgets
    -0.66
    StoryboardSegue
    -0.65
     استنادى
    -0.65
    CppMethod
    -0.64
    POSITIVE LOGITS
    ting
    0.69
    Output
    0.65
    output
    0.62
    ted
    0.60
     Output
    0.60
    OUTPUT
    0.59
    setInput
    0.57
     输入
    0.57
     into
    0.56
    输出
    0.56
    Activations Density 0.113%

    No Known Activations