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. 30329
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to various industries and medical contexts

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

    foreign language terms

    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
    OCCURRED
    -0.52
    __(/*!
    -0.52
     doInBackground
    -0.52
     kaynağından
    -0.52
    InputBorder
    -0.51
    󠁴
    -0.51
     initComponents
    -0.50
    initComponents
    -0.50
    帖最后由
    -0.50
     RIPRODUZIONE
    -0.50
    POSITIVE LOGITS
    WebServlet
    0.40
     voors
    0.34
     urma
    0.30
    انجليز
    0.29
    随
    0.29
    上がった
    0.28
     iyong
    0.27
     hechos
    0.27
    Portály
    0.26
     manifestazione
    0.26
    Activations Density 0.071%

    No Known Activations