© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15335
    Prev
    Next
    INDEX
    Explanations

    directional language and navigation instructions

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

    Road names or street addresses

    np_acts-logits-general · gemini-2.0-flash

    street names and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.63
    :+:
    -0.60
     Domes
    -0.57
    ########.
    -0.54
    hood
    -0.54
     sèche
    -0.53
    underland
    -0.53
     domes
    -0.52
    astify
    -0.52
     Assy
    -0.52
    POSITIVE LOGITS
     Main
    0.80
    Main
    0.64
     calle
    0.63
     Market
    0.60
     main
    0.59
    AccessFile
    0.58
     MonoBehaviour
    0.58
     Church
    0.57
     avenida
    0.56
    èdia
    0.56
    Activations Density 0.157%

    No Known Activations