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. 15588
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical data presentation and analysis

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

    "as" followed by percentages

    np_acts-logits-general · gemini-2.0-flash

    percentage and proportion

    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
    帖最后由
    -0.55
     للاسماء
    -0.49
    ंदीखरीदारी
    -0.47
    存于互联网档案馆
    -0.40
    IsContent
    -0.38
    CloseOperation
    -0.38
    ">//
    -0.38
    BeginInit
    -0.38
    市镇
    -0.37
    Toss
    -0.37
    POSITIVE LOGITS
     percentage
    2.28
     proportion
    2.16
     percentages
    1.96
    percentage
    1.84
     porcentaje
    1.80
     Percentage
    1.80
    Percentage
    1.76
    proportion
    1.76
     percent
    1.71
     pourcentage
    1.71
    Activations Density 0.879%

    No Known Activations