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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 78745
    Prev
    Next
    INDEX
    Explanations

    instances of monetary values, specifically in the context of legal discussions

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

    dollar amounts and numbers

    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
     betweenstory
    -0.88
    الحياه
    -0.77
     FetchType
    -0.65
     يتيمه
    -0.63
    OGND
    -0.58
    inSlope
    -0.57
     esternos
    -0.57
     препратки
    -0.56
    出版年
    -0.56
    queryInterface
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.82
    ViewFeatures
    0.47
    StructEnd
    0.44
     contextLoads
    0.41
     trate
    0.39
     AssemblyCulture
    0.36
     uman
    0.35
     purpoſe
    0.35
     rând
    0.35
    SaveChangesAsync
    0.34
    Activations Density 0.000%

    No Known Activations