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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6349
    Prev
    Next
    INDEX
    Explanations

    references to mathematical symbols and related formatting commands in programming or typesetting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedSize
    -0.72
    ()")
    -0.70
     localVar
    -0.65
    lasi
    -0.65
    ⇑
    -0.65
    aringan
    -0.63
    tagHelperRunner
    -0.63
    FormTagHelper
    -0.62
    iempos
    -0.62
     Vene
    -0.61
    POSITIVE LOGITS
     通販
    0.72
     AssemblyCulture
    0.69
     QtGui
    0.68
    WebServlet
    0.66
    ftagPool
    0.64
    principalTable
    0.63
    AnimationsModule
    0.62
     USP
    0.60
    InteropServices
    0.59
    はじめに
    0.56
    Activations Density 0.011%

    No Known Activations