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. 20-GEMMASCOPE-RES-131K
    6. 113387
    Prev
    Next
    INDEX
    Explanations

    references to procedural or technical details in a scientific context

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

    functional verbs and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.88
    
    -0.60
    tonode
    -0.59
     بيها
    -0.53
    richTextPanel
    -0.51
    はじめに
    -0.46
    帖最后由
    -0.46
    éez
    -0.46
    ̈́
    -0.45
    crapers
    -0.45
    POSITIVE LOGITS
    SuspendLayout
    0.43
    AutoField
    0.39
    RectangleBorder
    0.37
     disambiguazione
    0.36
    Бахар
    0.36
    -------------</
    0.35
    disposing
    0.35
    띄
    0.33
    dafx
    0.33
    atimes
    0.33
    Activations Density 0.063%

    No Known Activations