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. 9-GEMMASCOPE-RES-16K
    6. 3860
    Prev
    Next
    INDEX
    Explanations

    instances of structured data representations such as tables and arrays in the text

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

    LaTeX arrays or tables

    np_acts-logits-general · gemini-2.0-flash

    LaTeX arrays and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
     يتيمه
    -0.80
    findpost
    -0.74
     ویکی‌پدی
    -0.70
    帖最后由
    -0.60
    OGND
    -0.57
     autorytatywna
    -0.54
     صوتيه
    -0.54
    httphttps
    -0.54
     المعيارى
    -0.53
     propOrder
    -0.52
    POSITIVE LOGITS
    ᵕ
    0.46
    izer
    0.44
    endpush
    0.44
     Visser
    0.42
     endwhile
    0.41
     Walkover
    0.40
    fxml
    0.39
    ؤلاء
    0.39
     paramString
    0.39
    drawSprites
    0.39
    Activations Density 0.076%

    No Known Activations