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. 13767
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Br."

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

    Precedes an abbreviation, punctuation, or foreign word

    np_acts-logits-general · gemini-2.0-flash

    Br followed by various tokens

    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
    sego
    -0.65
    findpost
    -0.61
    verwijspagina
    -0.59
    endphp
    -0.59
    Datuak
    -0.56
     snippetHide
    -0.53
     sé
    -0.50
     RouterModule
    -0.49
     الرياضيه
    -0.49
    hyrchwyd
    -0.48
    POSITIVE LOGITS
     Allí
    0.54
    lliant
    0.52
     balanceOf
    0.52
    chooser
    0.50
     ICollection
    0.48
    forKey
    0.47
    liant
    0.47
    centralwidget
    0.46
    utal
    0.46
    WireFormatLite
    0.45
    Activations Density 0.122%

    No Known Activations