© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5543
    Prev
    Next
    INDEX
    Explanations

    references to proteins and their classifications in biological processes

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

    "multiple" or plurality

    np_acts-logits-general · gemini-2.0-flash

    multiple classifications

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     שוליים
    -0.52
    Portale
    -0.46
     tasse
    -0.43
    Források
    -0.41
    گذ
    -0.40
    toPromise
    -0.39
    斐
    -0.39
    Sú
    -0.39
    ubarak
    -0.39
    hassee
    -0.38
    POSITIVE LOGITS
     multiple
    1.05
     múltiple
    1.04
     multiplicity
    1.00
     Multiple
    0.97
     MULTIPLE
    0.95
    Multiple
    0.92
    multiple
    0.91
    MULTIPLE
    0.81
     múltip
    0.80
     múltiples
    0.79
    Activations Density 0.944%

    No Known Activations