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. 3-GEMMASCOPE-RES-16K
    6. 5883
    Prev
    Next
    INDEX
    Explanations

    references to tongue diagnostics in traditional Chinese medicine

    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
    Портал
    -0.71
     Untersch
    -0.64
    ViewImports
    -0.64
    ADELPHIA
    -0.64
     courriel
    -0.63
    BrowserModule
    -0.63
    sä
    -0.61
    ochet
    -0.61
    SequentialGroup
    -0.60
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     incentives
    0.70
     pulmonar
    0.68
    vin
    0.67
    Langue
    0.66
     tongue
    0.65
    ScopeManager
    0.59
    AndEndTag
    0.58
     Incentives
    0.58
     Glanz
    0.58
    Ross
    0.58
    Activations Density 0.690%

    No Known Activations