Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 772
    Prev
    Next
    INDEX
    Explanations

    references to UI controls and their associated properties or events

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

    terms related to user interface controls, specifically focusing on sliders and their value changes

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

    control and ctrl variations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    OGND
    -0.69
     województwie
    -0.66
    TypedDataSet
    -0.65
    DoubleQuotes
    -0.64
    Naissance
    -0.62
    modb
    -0.60
    verständlich
    -0.56
    becken
    -0.55
    ธ์
    -0.55
     memoized
    -0.54
    POSITIVE LOGITS
     control
    1.09
     Control
    1.05
     CONTROL
    0.99
    control
    0.98
     ctrl
    0.96
    ctrl
    0.94
    Control
    0.92
    CONTROL
    0.82
     Ctrl
    0.81
     ctl
    0.81
    Activations Density 0.018%

    No Known Activations