© 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. 28-GEMMASCOPE-RES-16K
    11. 5968
    Prev
    Next
    INDEX
    Explanations

    instances of spatial relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nearness or proximity

    np_acts-logits-general · gemini-2.0-flash

    proximity or distance measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bigger
    -0.35
     StatefulWidget
    -0.35
     Wider
    -0.35
    long
    -0.35
    "});
    -0.35
    Longer
    -0.34
    Long
    -0.34
    longed
    -0.34
    久
    -0.33
     añ
    -0.33
    POSITIVE LOGITS
     close
    1.43
     closeness
    1.29
     proximity
    1.16
     CLOSE
    1.10
     Close
    1.10
    close
    1.09
    Close
    1.01
     близь
    0.99
     closest
    0.99
     نزدیک
    0.98
    Activations Density 0.471%

    No Known Activations