© 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. 616
    Prev
    Next
    INDEX
    Explanations

    ratings and rankings related to media content or events

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

    mentions of ratings and rankings in media contexts

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

    counting consecutive periods

    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
     <=",
    -0.74
     للمعارف
    -0.71
    BibitemShut
    -0.67
    ]")]
    -0.63
     مواليد
    -0.62
    Zitat
    -0.61
    RectangleBorder
    -0.60
    bibfield
    -0.59
    ousands
    -0.59
    ositol
    -0.58
    POSITIVE LOGITS
     each
    1.19
     every
    1.03
    each
    0.98
     consecutive
    0.88
     setiap
    0.86
     каждый
    0.86
     both
    0.85
    every
    0.85
     three
    0.85
     EACH
    0.84
    Activations Density 0.121%

    No Known Activations