© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13642
    Prev
    Next
    INDEX
    Explanations

    the introductory phrase in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <%=
    -0.52
     fratelli
    -0.51
     brachte
    -0.50
     aikana
    -0.49
     brancas
    -0.48
     jäsen
    -0.48
     fatica
    -0.47
    Sklici
    -0.47
     keskus
    -0.45
     gând
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.96
    Portale
    0.89
     незавершена
    0.82
    esgue
    0.72
    Portail
    0.72
     StatefulWidget
    0.71
    InjectAttribute
    0.68
    :✨
    0.67
    windowFixed
    0.67
    GEBURTSDATUM
    0.66
    Activations Density 0.221%

    No Known Activations