© 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. 15655
    Prev
    Next
    INDEX
    Explanations

    pronouns and phrases indicating personal relationships or connections

    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
     averaged
    -0.56
    ores
    -0.43
     other
    -0.41
     vergangenen
    -0.40
     past
    -0.40
    kovo
    -0.38
    кон
    -0.38
     area
    -0.37
    HO
    -0.37
     using
    -0.37
    POSITIVE LOGITS
    XtraGrid
    0.99
     مرئيه
    0.97
    setVerticalGroup
    0.91
    الحياه
    0.84
     Lightboxes
    0.84
    QMetaType
    0.83
    expandindo
    0.78
     comigo
    0.76
    ьажоргаш
    0.76
    قایناق‌لار
    0.76
    Activations Density 0.208%

    No Known Activations