© 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. 20-GEMMASCOPE-RES-16K
    11. 13034
    Prev
    Next
    INDEX
    Explanations

    starting phrases or initialization markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himſelf
    -0.67
     myſelf
    -0.63
     themſelves
    -0.60
     uſed
    -0.59
     purpoſe
    -0.57
     pleaſure
    -0.56
     ſta
    -0.56
     itſelf
    -0.56
    ähteet
    -0.55
     raiſ
    -0.54
    POSITIVE LOGITS
     in
    1.00
     In
    0.88
    InThe
    0.74
     midst
    0.72
    inthe
    0.69
     IN
    0.68
     within
    0.67
     وفي
    0.66
     nella
    0.66
     isIn
    0.66
    Activations Density 0.274%

    No Known Activations