© 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. 39-GEMMASCOPE-RES-16K
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    references to knowledge bases or articles

    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
     '\\;'
    -0.48
    Ծանոթ
    -0.40
    ℗
    -0.38
    ↹
    -0.36
    ashian
    -0.36
    AutoModerator
    -0.35
    ophores
    -0.35
     Southwark
    -0.34
    youts
    -0.33
    ỡng
    -0.33
    POSITIVE LOGITS
     article
    3.84
     articles
    3.45
     Article
    3.44
    article
    3.16
    Article
    3.08
     Articles
    3.00
     ARTICLE
    2.97
    articles
    2.70
     Artikel
    2.69
    Articles
    2.63
    Activations Density 0.688%

    No Known Activations