© 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. 8052
    Prev
    Next
    INDEX
    Explanations

    references to world records and large-scale celebrations

    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
    tagHelperRunner
    -0.51
    -------------</
    -0.43
     kasarigan
    -0.39
    WithIOException
    -0.39
    Willkommen
    -0.38
    ArrowToggle
    -0.37
     referrerpolicy
    -0.35
     stá
    -0.35
     كومونز
    -0.35
    Välkommen
    -0.34
    POSITIVE LOGITS
     рекор
    0.73
     rekord
    0.69
     Guinness
    0.68
     record
    0.64
     RECORD
    0.62
     Rekord
    0.60
    record
    0.59
     récord
    0.56
    記録
    0.52
    Record
    0.51
    Activations Density 0.270%

    No Known Activations