© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1426
    Prev
    Next
    INDEX
    Explanations

    elements related to personal and creative writing including essays and short stories

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

    references to personal narratives or essays in non-fiction literature

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

    essays and short stories

    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
    Хьажоргаш
    -0.64
    GEBURTSDATUM
    -0.58
     وتسجيلات
    -0.58
     GenerationType
    -0.57
    cèse
    -0.55
     Novels
    -0.53
     referenties
    -0.52
    partiet
    -0.52
    SpringBootTest
    -0.52
     absoluto
    -0.52
    POSITIVE LOGITS
     essay
    0.71
     Essay
    0.60
     essays
    0.57
     Essays
    0.54
    Essay
    0.52
    LookAnd
    0.52
    essay
    0.49
     ess
    0.48
    mány
    0.47
    GIVEREF
    0.47
    Activations Density 0.155%

    No Known Activations