© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11736
    Prev
    Next
    INDEX
    Explanations

    personal connections and experiences related to relationships and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dalam
    -0.84
     într
    -0.70
     trong
    -0.70
    dalam
    -0.68
     katika
    -0.67
     darin
    -0.65
     dans
    -0.65
     במס
    -0.62
     Dalam
    -0.60
     dedans
    -0.59
    POSITIVE LOGITS
     near
    0.76
     locally
    0.72
     south
    0.70
     north
    0.70
    near
    0.66
    Near
    0.64
     Near
    0.60
     here
    0.59
     בישראל
    0.59
     Locally
    0.58
    Activations Density 0.659%

    No Known Activations