© 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. 141
    Prev
    Next
    INDEX
    Explanations

    financial figures and projections

    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
     stuff
    -1.24
     thingy
    -1.19
     something
    -0.98
    something
    -0.98
     montón
    -0.94
     things
    -0.90
     guys
    -0.90
     thing
    -0.89
     dingen
    -0.89
    whatever
    -0.88
    POSITIVE LOGITS
     approximately
    0.70
     utilized
    0.63
     existing
    0.60
     utilizing
    0.57
     commercially
    0.57
    较为
    0.56
     additional
    0.56
     formalized
    0.56
     Approximately
    0.55
     utilizes
    0.54
    Activations Density 2.239%

    No Known Activations