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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3795
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, particularly those used in monetary or mathematical contexts

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

    TeX math mode, monetary symbols, and other symbols

    np_acts-logits-general · gemini-2.0-flash

    special characters and code elements

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RenderAtEndOf
    -0.77
     surla
    -0.76
    ChildScrollView
    -0.68
    MLLoader
    -0.66
    DoubleQuotes
    -0.66
    Ӕ
    -0.63
     الاطلاع
    -0.62
    MessageTagHelper
    -0.61
     CURLOPT
    -0.59
    ьаж
    -0.58
    POSITIVE LOGITS
    PutPixel
    0.33
     idyl
    0.30
     contra
    0.28
    льевич
    0.26
    withOpacity
    0.26
    OptionsMenu
    0.25
    BagLayout
    0.25
    /***/
    0.25
    ForResult
    0.24
     antigu
    0.24
    Activations Density 0.179%

    No Known Activations