© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    references to procedures and compliance related to regulatory directives

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

    make clear or possible

    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
    killer
    -0.45
     du
    -0.40
     —
    -0.39
     Du
    -0.39
     soutient
    -0.38
    glDelete
    -0.38
    make
    -0.37
    不良
    -0.37
     делают
    -0.37
    gar
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.91
     betweenstory
    0.91
     BoxFit
    0.91
     alive
    0.90
     available
    0.83
     possible
    0.82
     AssemblyCulture
    0.82
     tartalomajánló
    0.81
     posible
    0.77
    ContentAsync
    0.76
    Activations Density 0.146%

    No Known Activations