© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12329
    Prev
    Next
    INDEX
    Explanations

    dates and specific references to time-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Months of the year

    np_acts-logits-general · gemini-2.0-flash

    months of the year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.65
    ThroughAttribute
    -0.65
    httphttps
    -0.64
    antMatchers
    -0.63
    sizeCache
    -0.62
     modelAndView
    -0.62
    uxxxx
    -0.61
    IsContent
    -0.60
    ỡng
    -0.59
    Personensuche
    -0.57
    POSITIVE LOGITS
     June
    0.68
     December
    0.65
     July
    0.64
     March
    0.64
     April
    0.63
     February
    0.62
    December
    0.61
    June
    0.57
     November
    0.57
     September
    0.57
    Activations Density 0.200%

    No Known Activations