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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    closing braces and other syntactical elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces in code blocks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     changes
    -0.56
     change
    -0.54
     kaarangay
    -0.41
     CHANGE
    -0.40
    changes
    -0.39
     chang
    -0.38
     Veränderung
    -0.38
    Changes
    -0.38
     changed
    -0.38
    Change
    -0.38
    POSITIVE LOGITS
     otherwise
    2.25
     Otherwise
    2.16
    Otherwise
    2.11
    otherwise
    2.05
     OTHERWISE
    1.77
     altrimenti
    1.63
     else
    1.59
     sonst
    1.55
    否则
    1.55
     иначе
    1.50
    Activations Density 0.134%

    No Known Activations