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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16315
    Prev
    Next
    INDEX
    Explanations

    information related to safety standards and regulations for toys

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

    Start of new turn with user text

    np_acts-logits-general · gemini-2.0-flash

    standards and compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     okuyayım
    -0.42
    LayoutStyle
    -0.41
    varlak
    -0.41
     onderhoud
    -0.38
     menac
    -0.38
     виправивши
    -0.38
    CompilerServices
    -0.38
     hunne
    -0.37
     Dres
    -0.37
     recommandée
    -0.37
    POSITIVE LOGITS
     Conform
    0.62
     conformity
    0.59
    Conform
    0.57
     RoHS
    0.54
     CE
    0.54
    conform
    0.53
     conforms
    0.52
     UL
    0.52
     compliance
    0.52
     certification
    0.50
    Activations Density 0.080%

    No Known Activations