© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54276
    Prev
    Next
    INDEX
    Explanations

    words related to tracking and managing movement in navigational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.48
    rzost
    -0.40
    share
    -0.39
    Cyfarwyddwr
    -0.38
    chartInstance
    -0.38
     lavabo
    -0.36
     Viena
    -0.35
     Quantitative
    -0.35
     Verſ
    -0.35
    Quantitative
    -0.35
    POSITIVE LOGITS
     trails
    0.52
     convoy
    0.50
     trail
    0.48
     sumpay
    0.47
     saites
    0.46
    TRAILING
    0.46
    ponses
    0.46
     Trails
    0.45
     trailing
    0.45
     trailers
    0.44
    Activations Density 0.041%

    No Known Activations