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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35805
    Prev
    Next
    INDEX
    Explanations

    elements related to web development

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

    website attributes and links

    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
     InputDecoration
    -0.29
    区
    -0.28
    burgo
    -0.27
     Huss
    -0.27
    振り
    -0.27
    ECONDS
    -0.27
     kurzen
    -0.26
    LayoutStyle
    -0.26
    ふり
    -0.25
    []]
    -0.25
    POSITIVE LOGITS
    RegressionTest
    0.72
    ArgumentParser
    0.68
    出版年
    0.63
    MLLoader
    0.61
    期刊论文
    0.60
    StoryboardSegue
    0.59
    richTextPanel
    0.57
     AssemblyTitle
    0.56
    RTLU
    0.56
     CWE
    0.55
    Activations Density 0.003%

    No Known Activations