© 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. 2187
    Prev
    Next
    INDEX
    Explanations

    terms related to predefined or default profiles in a computer program

    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
     leveren
    -0.56
     schu
    -0.53
     aang
    -0.53
     drinken
    -0.51
    ffekt
    -0.51
     gev
    -0.50
     aank
    -0.50
     leef
    -0.50
     inz
    -0.50
     voet
    -0.49
    POSITIVE LOGITS
     para
    0.57
     más
    0.57
     también
    0.55
     donde
    0.55
     cuando
    0.54
     sobre
    0.54
     que
    0.54
     porque
    0.54
     como
    0.52
     mayor
    0.52
    Activations Density 1.018%

    No Known Activations