© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    references to medical test results and their implications

    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
     accomod
    -0.72
     (!)
    -0.68
    (!)
    -0.67
     ostensibly
    -0.66
     poichè
    -0.66
    🏻‍♀️
    -0.63
     ~$
    -0.62
     presumably
    -0.61
     gibts
    -0.61
    Additionally
    -0.59
    POSITIVE LOGITS
     dose
    0.57
     witch
    0.51
     giebt
    0.46
    Dose
    0.45
     defi
    0.44
     strait
    0.43
     Dose
    0.42
     ether
    0.42
    [[
    0.42
     fallow
    0.41
    Activations Density 0.349%

    No Known Activations