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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7812
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or expressions that indicate functions or variables

    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
    iettivo
    -0.71
     Kyoto
    -0.68
     McGee
    -0.68
    oporosis
    -0.68
    rtype
    -0.67
    Trotz
    -0.66
     fees
    -0.65
     Klee
    -0.65
    ✖
    -0.63
     yogurt
    -0.63
    POSITIVE LOGITS
     Str
    1.03
    tilde
    1.00
    Str
    0.86
    middels
    0.83
    soever
    0.77
     aged
    0.69
     sœur
    0.64
     Shum
    0.64
    Mund
    0.64
    winder
    0.64
    Activations Density 0.073%

    No Known Activations