© 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. 13-GEMMASCOPE-RES-65K
    6. 57495
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases related to time and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chitis
    -0.62
     Mendelssohn
    -0.59
     Lourdes
    -0.56
    addCriterion
    -0.55
     Himalayas
    -0.55
    jedis
    -0.54
     hornblende
    -0.54
    consola
    -0.53
     Paddington
    -0.52
     francs
    -0.51
    POSITIVE LOGITS
    fromnode
    0.90
    WebServlet
    0.89
    Tembelea
    0.83
     disambiguazione
    0.81
     виправивши
    0.79
    setof
    0.73
    Früh
    0.71
    GEBURTSDATUM
    0.71
    InSection
    0.68
    ThemeOverlay
    0.67
    Activations Density 0.027%

    No Known Activations