© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 306
    Prev
    Next
    INDEX
    Explanations

    key terms related to organizational roles and leadership

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

    preceding "at"

    np_acts-logits-general · gemini-2.0-flash

    affiliation at

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.87
    ReusableCell
    -0.83
     ſche
    -0.77
     beginnetje
    -0.76
     nahilalakip
    -0.76
    PyExc
    -0.76
    aarrggbb
    -0.76
    GEBURTSDATUM
    -0.75
     ModelExpression
    -0.73
    tvguidetime
    -0.72
    POSITIVE LOGITS
     at
    2.39
     presso
    1.72
     tại
    1.69
     chez
    1.33
     	e
    1.15
    At
    1.10
    at
    1.08
     At
    1.03
     בבית
    1.02
     ở
    0.90
    Activations Density 0.738%

    No Known Activations