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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55950
    Prev
    Next
    INDEX
    Explanations

    references to Noah and the Ark in a historical or metaphorical context

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

    Noah, ark, flood, Ham

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    swire
    -0.47
     Buckingham
    -0.44
     nimble
    -0.42
     crumbs
    -0.42
     ioutil
    -0.41
     tweaked
    -0.41
     bulun
    -0.41
     meisjes
    -0.41
    setopt
    -0.41
    posizioni
    -0.41
    POSITIVE LOGITS
     Noah
    0.56
    Noah
    0.54
    oredCriteria
    0.48
    ViewImports
    0.48
     juſ
    0.47
     onAnimation
    0.46
     ſta
    0.44
    المشاركات
    0.43
     beginnetje
    0.43
     незавершена
    0.42
    Activations Density 0.006%

    No Known Activations