© 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. 4865
    Prev
    Next
    INDEX
    Explanations

    structured data points and organizational components related to varying categories

    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
     jScrollPane
    -0.65
     milliers
    -0.60
     berbagai
    -0.57
     centaines
    -0.56
    ต่างๆ
    -0.55
     tartalomajánló
    -0.55
     Fassung
    -0.52
     pelbagai
    -0.52
     birçok
    -0.52
     Wiktionnaire
    -0.52
    POSITIVE LOGITS
     apiece
    1.19
     namely
    1.02
     totaling
    0.91
     each
    0.91
     plus
    0.89
     totalling
    0.88
    分別
    0.85
    分别是
    0.85
     consecutively
    0.85
    namely
    0.80
    Activations Density 0.863%

    No Known Activations