© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15715
    Prev
    Next
    INDEX
    Explanations

    specific phrases or references associated with French publications and their critique of political ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.99
     >=",
    -0.88
     <=",
    -0.83
     autorytatywna
    -0.82
     виправивши
    -0.82
     BorderRadius
    -0.79
     BIBSYS
    -0.79
    extAlignment
    -0.78
    afficheront
    -0.77
    ductory
    -0.77
    POSITIVE LOGITS
     pomo
    0.49
     Point
    0.49
     lomb
    0.48
     Correspond
    0.47
     Mathis
    0.47
    所
    0.46
     sombre
    0.46
     đẩy
    0.46
     fil
    0.46
    È
    0.46
    Activations Density 3.071%

    No Known Activations