© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 12500
    Prev
    Next
    INDEX
    Explanations

    references to communication or messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.48
     disponibilités
    -0.41
    orianCalendar
    -0.39
    lankton
    -0.39
    CompoundButton
    -0.38
     transfieras
    -0.38
     utafitiHapana
    -0.37
     femininas
    -0.32
    ้อมูล
    -0.31
     Mammal
    -0.30
    POSITIVE LOGITS
     message
    3.25
     messages
    2.95
     Message
    2.80
    message
    2.70
     Messages
    2.61
     MESSAGE
    2.58
    Message
    2.53
     msg
    2.48
    メッセージ
    2.38
    MESSAGE
    2.31
    Activations Density 0.821%

    No Known Activations