© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5062
    Prev
    Next
    INDEX
    Explanations

    concepts related to faith, thoughtfulness, and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.46
    Autoritní
    -0.39
     vast
    -0.36
    IntoConstraints
    -0.36
     miſ
    -0.34
     HomeController
    -0.34
     <>",
    -0.34
     bogus
    -0.34
     مشين
    -0.34
     faſt
    -0.33
    POSITIVE LOGITS
    fulness
    2.11
    ful
    2.11
    FUL
    1.94
    fully
    1.88
    full
    1.66
    FULLY
    1.57
    Ful
    1.45
     ful
    1.39
    FULL
    1.39
    fuls
    1.37
    Activations Density 0.211%

    No Known Activations