Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2907
    Prev
    Next
    INDEX
    Explanations

    references to extreme conditions and fluctuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()")
    -0.45
    StoryboardSegue
    -0.44
     daff
    -0.44
     diver
    -0.39
     fibre
    -0.39
     courtes
    -0.39
     Fibre
    -0.38
    \|^{
    -0.38
    accus
    -0.37
    Hello
    -0.37
    POSITIVE LOGITS
     estekak
    0.62
     baseline
    0.61
     extreme
    0.58
     extrême
    0.57
    extreme
    0.57
     extremes
    0.53
     secours
    0.51
     report
    0.51
     AssemblyCulture
    0.50
     BorderSide
    0.50
    Activations Density 0.139%

    No Known Activations