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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 513
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those relating to measurements or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kitab
    -0.62
     saites
    -0.59
    orianCalendar
    -0.58
    courir
    -0.57
    __[
    -0.57
     zapato
    -0.55
    ivotopis
    -0.55
    XmlSchema
    -0.53
    akyti
    -0.52
    Longueur
    -0.52
    POSITIVE LOGITS
     Millionen
    0.70
     miljoen
    0.62
     milion
    0.61
     млн
    0.58
     millioner
    0.57
     milioni
    0.57
     Million
    0.56
     '\\;'
    0.56
     million
    0.55
     MILLION
    0.55
    Activations Density 0.649%

    No Known Activations