© 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. 5173
    Prev
    Next
    INDEX
    Explanations

    references to routine or repetitive occurrences

    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
    Days
    -1.27
     Days
    -1.19
    DAYS
    -1.16
    Weeks
    -1.13
     DAYS
    -1.07
    days
    -1.07
    weeks
    -1.02
    Nights
    -1.02
    nights
    -1.00
     Weeks
    -0.98
    POSITIVE LOGITS
     say
    0.54
     da
    0.40
     faithful
    0.38
     dy
    0.37
     clay
    0.36
     bleek
    0.35
     dat
    0.34
     says
    0.33
    aperto
    0.33
     nyt
    0.33
    Activations Density 0.259%

    No Known Activations