© 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. 33-GEMMASCOPE-RES-16K
    11. 9074
    Prev
    Next
    INDEX
    Explanations

    proximity-related terms indicating closeness to people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.50
     typelib
    -0.44
     SwitchCompat
    -0.39
     viewDidLoad
    -0.38
     steeper
    -0.37
     doInBackground
    -0.36
     carottes
    -0.36
    湃
    -0.36
    DOCTYPE
    -0.35
     actionTypes
    -0.35
    POSITIVE LOGITS
     proximity
    0.96
     Proximity
    0.78
    knit
    0.70
     Close
    0.66
    close
    0.66
     knit
    0.66
    Close
    0.65
     closeness
    0.65
    Proximity
    0.64
     proxim
    0.63
    Activations Density 0.071%

    No Known Activations