© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3070
    Prev
    Next
    INDEX
    Explanations

    the term "compared" indicating comparisons or contrasts in data and findings

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

    compared with/to

    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
    :✨
    -0.65
     intStringLen
    -0.54
     ExecuteAsync
    -0.53
    thâu
    -0.50
    principalTable
    -0.49
    WebElementEntity
    -0.49
     Chwiliwch
    -0.47
    onChanged
    -0.47
    enumi
    -0.47
    ddots
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.69
     compared
    0.65
     שוליים
    0.59
     '\\;'
    0.58
    compared
    0.58
     favourably
    0.57
     compar
    0.57
    afficheront
    0.56
     Compar
    0.56
    couvrez
    0.56
    Activations Density 0.036%

    No Known Activations