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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3327
    Prev
    Next
    INDEX
    Explanations

    HTML or CSS attributes related to dimensions and spacing

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

    CSS height property or related terms

    np_acts-logits-general · gemini-2.0-flash

    height: dimension values

    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
     CreateTagHelper
    -0.56
     ویکی‌پدیا
    -0.56
    tagPool
    -0.55
    ftagPool
    -0.55
    RotationOrder
    -0.54
    fjspx
    -0.52
    webElementXpaths
    -0.51
     utafitiHapana
    -0.50
    Personensuche
    -0.49
     kasarigan
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.90
    height
    0.82
     height
    0.78
    Height
    0.74
     HEIGHT
    0.74
    HEIGHT
    0.72
     Height
    0.70
     heights
    0.57
    getHeight
    0.56
     hauteur
    0.54
    Activations Density 0.214%

    No Known Activations