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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10920
    Prev
    Next
    INDEX
    Explanations

    references to ice cream and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    existsSync
    -0.68
     thiệu
    -0.61
    logrus
    -0.60
    ogens
    -0.58
    таратура
    -0.57
     geometric
    -0.57
    ULDER
    -0.57
    chey
    -0.56
     FRAME
    -0.56
     fracas
    -0.56
    POSITIVE LOGITS
    Kid
    1.01
     Kid
    0.92
    kid
    0.82
     AssemblyCulture
    0.82
     KID
    0.75
    KID
    0.71
     needle
    0.71
    WebServlet
    0.70
    GraphicsUnit
    0.70
     kid
    0.66
    Activations Density 0.382%

    No Known Activations