© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57393
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to button styles and outlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.75
     SafeMath
    -0.71
     recevrez
    -0.68
     *)__
    -0.66
     NACIONAL
    -0.66
    <?
    -0.60
    uxxxx
    -0.59
    atmosphère
    -0.58
     ExecuteAsync
    -0.57
    chyma
    -0.56
    POSITIVE LOGITS
    outline
    1.56
    Outline
    0.93
     Outline
    0.87
    OCCURRED
    0.82
     OUTLINE
    0.81
     outline
    0.78
     kasarigan
    0.66
     esboço
    0.62
     Toulon
    0.59
     Kaye
    0.55
    Activations Density 0.003%

    No Known Activations