© 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. 39-GEMMASCOPE-RES-16K
    11. 2861
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to bacteria and their biochemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phthal
    -0.40
     betweenstory
    -0.40
    flash
    -0.39
    fox
    -0.39
    Ful
    -0.37
     للاسماء
    -0.37
    floral
    -0.36
    film
    -0.36
     Kombat
    -0.36
    files
    -0.36
    POSITIVE LOGITS
     fe
    2.28
     Fe
    2.28
    Fe
    2.16
     FE
    2.14
    fe
    1.91
    FE
    1.90
     Fé
    1.84
    フェ
    1.84
     Fed
    1.80
     FED
    1.76
    Activations Density 2.032%

    No Known Activations