© 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. 20-GEMMASCOPE-RES-16K
    6. 6308
    Prev
    Next
    INDEX
    Explanations

    specific months and their occurrences within the text

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

    months of the year, particularly November.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     игрушки
    -0.40
    sup
    -0.40
    atic
    -0.37
    sträger
    -0.37
    SharedCtor
    -0.37
    super
    -0.36
    big
    -0.36
     drone
    -0.36
     сидит
    -0.36
     вижу
    -0.35
    POSITIVE LOGITS
     October
    1.14
     November
    1.13
     December
    1.12
     February
    1.12
     September
    1.10
    December
    1.09
     January
    1.06
    November
    1.05
    October
    1.05
    February
    1.03
    Activations Density 0.125%

    No Known Activations