© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2974
    Prev
    Next
    INDEX
    Explanations

    specific sequences and patterns associated with experimental procedures and measurements

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

    programming or technical code sequences with looping, counting, and iteration syntax.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    numbers and counting sequences, particularly when referencing multiple iterations, cycles, or times.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Мексичка
    -0.54
     مشين
    -0.53
    contentLoaded
    -0.52
     CGRectMake
    -0.48
     betweenstory
    -0.48
     للمعارف
    -0.47
    setVerticalGroup
    -0.47
    extAlignment
    -0.47
    !*\
    -0.47
    DockStyle
    -0.47
    POSITIVE LOGITS
    回数
    0.64
     repeated
    0.59
     repetition
    0.56
     repeat
    0.53
     times
    0.52
     repetitions
    0.51
    繰り返
    0.49
     repeti
    0.46
    repeated
    0.46
    何回
    0.46
    Activations Density 0.436%

    No Known Activations