© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4373
    Prev
    Next
    INDEX
    Explanations

    instances of people or proper names referenced in a context

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

    Comes after honorifics (Mr., Ms., etc.)

    np_acts-logits-general · gemini-2.0-flash

    names following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gies
    -0.57
     Einwilligung
    -0.54
     ordinaires
    -0.54
     extérieures
    -0.51
     Internasional
    -0.51
     Kowal
    -0.50
     quelcon
    -0.50
     obě
    -0.49
     península
    -0.49
     vectorielles
    -0.49
    POSITIVE LOGITS
     Singh
    0.59
     Tarantino
    0.57
     Merkel
    0.56
     Berber
    0.56
     Pointer
    0.56
     Netanyahu
    0.56
     Vettel
    0.54
     Trudeau
    0.54
     Duterte
    0.54
     Williams
    0.54
    Activations Density 0.937%

    No Known Activations