© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8899
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.76
     tartalomajánló
    -0.70
    bewerken
    -0.68
    }")]
    -0.65
     autorytatywna
    -0.64
    windowFixed
    -0.63
    참고
    -0.63
     виправивши
    -0.63
    berdayakan
    -0.62
    ureusement
    -0.62
    POSITIVE LOGITS
    ero
    1.00
    era
    0.85
    eros
    0.82
    ERO
    0.79
    TagHelper
    0.77
    eri
    0.73
    ered
    0.70
    ern
    0.69
    erie
    0.66
    ery
    0.64
    Activations Density 1.959%

    No Known Activations