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. 35487
    Prev
    Next
    INDEX
    Explanations

    technical terms and entities related to programming languages and frameworks, particularly C, C++, and ASP.NET, as well as references to African identities and historical figures

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

    C++ or NET app

    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
     lenker
    -0.37
    过
    -0.31
    whose
    -0.30
     Notícias
    -0.29
     kohta
    -0.29
     büy
    -0.28
    있는
    -0.28
    chaften
    -0.28
     whose
    -0.28
     createSlice
    -0.27
    POSITIVE LOGITS
    CDCl
    0.65
     estadounid
    0.64
     dezelve
    0.63
    nosaurus
    0.63
    GeneratedMessage
    0.61
     zoude
    0.59
    casio
    0.59
     Geiſt
    0.58
    IBLIO
    0.58
     BorderRadius
    0.58
    Activations Density 0.151%

    No Known Activations