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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14277
    Prev
    Next
    INDEX
    Explanations

    coding concepts related to data structures and their implementations

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

    advice and conditional logic

    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
     nahilalakip
    -0.49
    <?
    -0.45
     وتسجيلات
    -0.45
    ſelves
    -0.44
    //
    -0.43
     Majefty
    -0.42
    最快更新
    -0.42
    MLLoader
    -0.41
     ſy
    -0.40
    BeginInit
    -0.40
    POSITIVE LOGITS
     dAtA
    0.60
    tagHelperRunner
    0.56
     informée
    0.56
     виправивши
    0.52
     intptr
    0.48
     &___
    0.44
     <>",
    0.44
    :]:
    0.44
    তথ্যসূত্র
    0.43
     ;)
    0.43
    Activations Density 0.026%

    No Known Activations