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. 24-GEMMASCOPE-RES-16K
    6. 4127
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" and related prepositions, indicating a focus on locations or timing

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

    Follows "On" and refers to dates/days

    np_acts-logits-general · gemini-2.0-flash

    on followed by date or day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.83
    ReusableCell
    -0.76
    UnknownFieldSet
    -0.74
    nodoc
    -0.62
     hâte
    -0.61
    CodedInputStream
    -0.61
     snippetHide
    -0.61
    BagLayout
    -0.60
    setVerticalGroup
    -0.60
    AddTagHelper
    -0.60
    POSITIVE LOGITS
    Билгалдахарш
    0.61
     offer
    0.57
    ViewImports
    0.55
    "])){
    0.55
     site
    0.52
     show
    0.51
     désolés
    0.47
     Show
    0.45
    Cyfeiriadau
    0.45
    show
    0.45
    Activations Density 0.120%

    No Known Activations