Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67561
    Prev
    Next
    INDEX
    Explanations

    terms related to pathogens, medical conditions, and genetic factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Begriffsklä
    -0.52
    MigrationBuilder
    -0.50
    Tembelea
    -0.49
     jspb
    -0.48
    SpringBootTest
    -0.46
    MatButtonModule
    -0.43
    XmlEnum
    -0.41
    XmlAccessType
    -0.41
    verwijspagina
    -0.40
     للمعارف
    -0.40
    POSITIVE LOGITS
     surla
    0.52
     ffilmiau
    0.44
     ومل
    0.41
     captured
    0.41
    introduced
    0.40
     hikariConfig
    0.39
    !("{}",
    0.39
    Derbyniad
    0.39
     anti
    0.38
     Carne
    0.38
    Activations Density 0.173%

    No Known Activations