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. 15604
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to web page layout and design

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

    HTML or CSS code snippets

    np_acts-logits-general · gemini-2.0-flash
    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
     StringTokenizer
    -0.53
    WebElementEntity
    -0.50
     UIAlert
    -0.46
    UserScript
    -0.46
    WireFormatLite
    -0.45
     notificaciones
    -0.44
    AutoModerator
    -0.44
    الدراسه
    -0.42
     MessageBoxIcon
    -0.40
    Rüyada
    -0.40
    POSITIVE LOGITS
     About
    0.48
     ABOUT
    0.48
     parallax
    0.46
    About
    0.45
     hero
    0.45
    about
    0.45
     Hero
    0.45
    ABOUT
    0.45
     CONTACT
    0.45
    Contact
    0.44
    Activations Density 0.099%

    No Known Activations