© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    instructions and guidance related to problem-solving and creativity

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

    references to children's activities and the concept of independence in learning

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

    fitting puzzle pieces

    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
     nahilalakip
    -0.59
     resourceCulture
    -0.58
    biamo
    -0.54
    ItemBackground
    -0.54
    zeptember
    -0.53
     kasarigan
    -0.52
     referenties
    -0.52
     xenia
    -0.51
    ^*)
    -0.51
     charters
    -0.51
    POSITIVE LOGITS
     pieces
    1.68
     puzzle
    1.56
     Pieces
    1.47
    pieces
    1.43
     jigsaw
    1.42
    Pieces
    1.37
     piec
    1.33
     piece
    1.29
     assembling
    1.27
     Puzzle
    1.27
    Activations Density 0.203%

    No Known Activations