© 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. 37-GEMMASCOPE-RES-16K
    11. 5383
    Prev
    Next
    INDEX
    Explanations

    references to judgment and moral authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seguida
    -0.33
     bols
    -0.26
     Consequently
    -0.25
     Revisited
    -0.25
    /#{
    -0.25
    ##
    -0.25
     Everybody
    -0.25
    我们就
    -0.24
    Everybody
    -0.24
    şağı
    -0.24
    POSITIVE LOGITS
     ſol
    0.74
    ſelves
    0.73
     ſal
    0.72
     faſt
    0.72
    ſelf
    0.72
     terrifying
    0.70
     ſta
    0.70
     ſever
    0.69
     ſehr
    0.68
     ſei
    0.68
    Activations Density 0.056%

    No Known Activations