© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1106
    Prev
    Next
    INDEX
    Explanations

    locations and directions related to paths and routes

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

    Follows prepositions of location

    np_acts-logits-general · gemini-2.0-flash

    location and spatial relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clovis
    -0.57
     POI
    -0.53
    dAtA
    -0.53
     Eury
    -0.52
     NEO
    -0.50
     Azo
    -0.50
     uli
    -0.49
     Bangor
    -0.49
     SIAM
    -0.49
     Manipur
    -0.49
    POSITIVE LOGITS
    Solución
    0.68
     Mount
    0.64
    tired
    0.64
     Folge
    0.63
    historic
    0.63
    webElementGuid
    0.63
    {§
    0.63
     historic
    0.63
    RectangleBorder
    0.60
    tonode
    0.59
    Activations Density 0.325%

    No Known Activations