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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8644
    Prev
    Next
    INDEX
    Explanations

    contextual connectors and emphasizing phrases in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.84
    MethodManager
    -0.73
    ConstraintMaker
    -0.68
    下载附件
    -0.65
    AccessorTable
    -0.65
     pinulongan
    -0.62
    complexContent
    -0.61
    PreferredItem
    -0.60
    RenderAtEndOf
    -0.60
     LoggerFactory
    -0.60
    POSITIVE LOGITS
     Wellen
    0.55
     legisl
    0.53
     مرئيه
    0.53
    LAHOMA
    0.52
    族館
    0.51
     federal
    0.50
     implemented
    0.49
    Appellee
    0.48
     enacted
    0.47
    cheduler
    0.47
    Activations Density 0.888%

    No Known Activations