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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53320
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the patient, alleged, liquid, grave, image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trás
    -0.53
    OGND
    -0.51
    EVT
    -0.50
    AssignableFrom
    -0.50
     cách
    -0.50
     estimés
    -0.50
    sizeCache
    -0.49
    entance
    -0.48
     assolu
    -0.46
     maintien
    -0.46
    POSITIVE LOGITS
    ^(@)
    0.64
    }")
    
    0.63
    SharedDtor
    0.62
    VELAND
    0.59
    chọn
    0.57
    setScene
    0.57
    ">—
    0.57
     horizons
    0.57
    consulté
    0.56
    Архівовано
    0.55
    Activations Density 0.124%

    No Known Activations