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. 122379
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical configurations and data parsing

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

    legal assistance and legal cases

    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
     Chwiliwch
    -0.68
     للاسماء
    -0.67
    日閲覧
    -0.56
     wireType
    -0.53
    HtmlAttribute
    -0.52
     typelib
    -0.48
     دریافت‌شده
    -0.48
    etheless
    -0.47
    WriteBarrier
    -0.46
    CppMethod
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.56
     Shell
    0.43
     Africa
    0.42
    Clik
    0.39
     Wheeler
    0.39
     Tas
    0.38
    дера
    0.38
     ABC
    0.38
     Cut
    0.37
     India
    0.36
    Activations Density 0.086%

    No Known Activations