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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15299
    Prev
    Next
    INDEX
    Explanations

    references to "InstanceState" and U.S. legal citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <b>
    -0.61
     "
    -0.61
    â
    -0.59
     '
    -0.59
    `
    -0.59
    b
    -0.58
    0
    -0.58
    w
    -0.58
    (
    -0.57
     
    -0.57
    POSITIVE LOGITS
    DoubleQuotes
    2.08
     ModelExpression
    2.00
     للمعارف
    1.77
    новништво
    1.73
    :✨
    1.67
    RegistryLite
    1.57
    AndEndTag
    1.55
    ViewFeatures
    1.54
    mybatisplus
    1.54
     للاسماء
    1.54
    Activations Density 0.017%

    No Known Activations