Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24377
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific and regulatory terminology, particularly related to substances and their classifications

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

    NH compounds and abbreviations

    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
    สู
    -0.30
    TableHead
    -0.30
    beginPath
    -0.28
    fillStyle
    -0.27
     verfü
    -0.27
     effectively
    -0.26
     counted
    -0.25
     مشارکت‌کنندگان
    -0.25
    apiKey
    -0.25
    richTextPanel
    -0.24
    POSITIVE LOGITS
     autorytatywna
    0.75
     NH
    0.73
     Nh
    0.72
     Anſ
    0.71
    +#+#
    0.68
     Reſ
    0.66
     pleaſure
    0.66
     ſever
    0.65
    NH
    0.65
     kasarigan
    0.64
    Activations Density 0.025%

    No Known Activations