© 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. 5430
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data input formatting and validation

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

    Tokens preceding CSS styles in React Native

    np_acts-logits-general · gemini-2.0-flash

    UI code and styles

    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
    rungsseite
    -0.87
     autorytatywna
    -0.74
    Bibliograf
    -0.74
    LookAnd
    -0.69
    
    -0.65
     ModelExpression
    -0.64
    homonymie
    -0.61
    apunov
    -0.60
    #
    -0.60
     noDo
    -0.60
    POSITIVE LOGITS
    anyard
    0.55
     style
    0.48
    style
    0.47
     vice
    0.45
    కి
    0.43
    manya
    0.43
     induced
    0.42
    Style
    0.42
     rowspan
    0.42
     gaya
    0.41
    Activations Density 0.029%

    No Known Activations