Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12707
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terminology related to systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.87
    Lähteet
    -0.83
     שוליים
    -0.81
    keyColumn
    -0.73
    
    -0.68
     ivelany
    -0.65
    ----</
    -0.64
    AnimationsModule
    -0.64
     विश्वसनीयता
    -0.63
     חיצוניים
    -0.63
    POSITIVE LOGITS
    <eos>
    1.06
    vacy
    0.58
    thenReturn
    0.55
    figer
    0.54
    edict
    0.51
    lassen
    0.50
    eace
    0.50
    λες
    0.49
    appé
    0.49
    ata
    0.48
    Activations Density 0.377%

    No Known Activations