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. 6-GEMMASCOPE-RES-16K
    6. 2470
    Prev
    Next
    INDEX
    Explanations

    baseball statistics and events

    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
     pelindung
    -0.56
     cabang
    -0.50
    τί
    -0.50
    zijde
    -0.50
     utilisons
    -0.49
     sebaliknya
    -0.49
     nő
    -0.47
     quitte
    -0.47
     nationaux
    -0.46
    verständlich
    -0.45
    POSITIVE LOGITS
    \{\\
    0.80
    WireFormatLite
    0.79
    Autoritní
    0.68
    QMetaType
    0.67
    GEBURTSDATUM
    0.65
     disambiguazione
    0.64
    setVerticalGroup
    0.64
    douard
    0.62
    OGND
    0.62
     autorytatywna
    0.61
    Activations Density 0.142%

    No Known Activations