© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6849
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS structure related to navigation and user interface elements

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

    header, body, or unit structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ویکی‌پدی
    -0.87
    GEBURTSDATUM
    -0.82
    istoitu
    -0.80
     يتيمه
    -0.76
     оригіналу
    -0.71
     autorytatywna
    -0.71
    ніципалі
    -0.71
    EDEFAULT
    -0.68
    parsedMessage
    -0.67
     فريبيس
    -0.67
    POSITIVE LOGITS
     header
    0.54
     body
    0.54
     head
    0.44
    body
    0.41
     front
    0.39
     Body
    0.38
     cabecera
    0.38
     Ste
    0.38
    header
    0.36
     heading
    0.36
    Activations Density 0.001%

    No Known Activations