© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    references to time and numerical quantities within expressions

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

    mathematical terms related to time and probability

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

    at time or step

    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
    NameInMap
    -0.79
    enumii
    -0.72
     للمعارف
    -0.71
    principalTable
    -0.71
    $_['
    -0.70
    収録曲
    -0.70
    Autoritní
    -0.69
     transfieras
    -0.69
    Datuak
    -0.68
    Tikang
    -0.67
    POSITIVE LOGITS
     position
    0.51
     time
    0.49
    index
    0.47
     index
    0.46
    时间
    0.46
     locations
    0.45
     history
    0.45
    indices
    0.43
    resti
    0.42
     positions
    0.42
    Activations Density 0.216%

    No Known Activations