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. 38-GEMMASCOPE-RES-16K
    6. 13334
    Prev
    Next
    INDEX
    Explanations

    references to player injuries and their impacts on sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.62
    IsContent
    -0.57
    ScopeManager
    -0.50
    InstrumentedTest
    -0.48
     CURIAM
    -0.46
    AndEndTag
    -0.45
    Personendaten
    -0.44
    EndContext
    -0.42
    rungsseite
    -0.42
     AssemblyTitle
    -0.42
    POSITIVE LOGITS
     impressed
    0.65
     finished
    0.61
     struggled
    0.60
     missed
    0.59
     enters
    0.54
     looms
    0.52
     flashed
    0.51
     Finished
    0.51
     enjoyed
    0.50
     averaged
    0.50
    Activations Density 0.198%

    No Known Activations