© 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. 40-GEMMASCOPE-RES-16K
    11. 6235
    Prev
    Next
    INDEX
    Explanations

    elements related to coding, specifically around programming conditions and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zó
    -0.54
    onson
    -0.53
    orian
    -0.52
    urion
    -0.52
    ecker
    -0.51
    olut
    -0.51
    lewood
    -0.50
    dames
    -0.50
     Heere
    -0.50
    onnen
    -0.50
    POSITIVE LOGITS
     @__
    0.52
     @@
    0.52
     |]
    0.51
      
    0.49
     <.
    0.49
     +-
    0.48
     /#
    0.48
     ,.
    0.48
     [][]
    0.48
     -:
    0.47
    Activations Density 0.748%

    No Known Activations