© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1491
    Prev
    Next
    INDEX
    Explanations

    terms related to the letter 'W'

    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
    padek
    -0.50
     McIn
    -0.50
    ondi
    -0.50
    miot
    -0.50
    Facades
    -0.50
     territoire
    -0.48
    digd
    -0.47
    inali
    -0.46
    冒
    -0.46
    ti
    -0.46
    POSITIVE LOGITS
    w
    1.39
    ww
    1.25
    wer
    1.20
    wi
    1.18
    wn
    1.17
    wed
    1.17
    we
    1.16
    war
    1.13
    wy
    1.12
    wo
    1.12
    Activations Density 0.281%

    No Known Activations