© 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. 21-GEMMASCOPE-RES-16K
    11. 11872
    Prev
    Next
    INDEX
    Explanations

    references to time durations and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosa
    -0.41
     rallado
    -0.40
     ért
    -0.39
     arose
    -0.38
     egyes
    -0.37
     cipolla
    -0.37
    rosas
    -0.36
    iocene
    -0.36
     pisau
    -0.36
     fábrica
    -0.35
    POSITIVE LOGITS
     months
    0.73
    weeks
    0.65
    months
    0.65
     weeks
    0.64
    Months
    0.62
     Months
    0.59
    __":
    0.57
     MONTHS
    0.57
    postsleuth
    0.56
    KommentareTeilen
    0.55
    Activations Density 0.386%

    No Known Activations