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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 37
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence delimiters that indicate structure in the text

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

    conditional statements or hypothetical situations

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

    contrast or explanation

    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
     AssemblyVersion
    -0.71
    AndEndTag
    -0.63
    interopRequire
    -0.60
    PageFactory
    -0.60
    __':
    -0.59
     désolés
    -0.59
     automatiques
    -0.59
     समीक्षाएं
    -0.59
     définiti
    -0.58
    GenerationType
    -0.56
    POSITIVE LOGITS
     put
    0.95
     add
    0.85
     take
    0.81
     introduce
    0.77
     combine
    0.72
     throw
    0.70
     ask
    0.70
     remove
    0.70
     Add
    0.69
     go
    0.69
    Activations Density 0.077%

    No Known Activations