© 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. 13-GEMMASCOPE-RES-16K
    11. 5833
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and proximity between locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.45
    ITUD
    -0.41
     long
    -0.37
     reading
    -0.36
     longe
    -0.35
    multirow
    -0.35
     mul
    -0.35
     tänka
    -0.35
    bien
    -0.34
    นาน
    -0.34
    POSITIVE LOGITS
    extAlignment
    0.63
     close
    0.63
    directly
    0.61
    nearby
    0.60
     nearby
    0.60
     CLOSE
    0.60
     adjacent
    0.59
     vicino
    0.58
     Close
    0.58
     proximity
    0.58
    Activations Density 0.410%

    No Known Activations