© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    specific locations, landmarks, and geographical features

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

    Proximity to a location

    np_acts-logits-general · gemini-2.0-flash

    places and proximity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SequentialGroup
    -1.06
     saites
    -0.94
     intptr
    -0.88
    #+#
    -0.84
     InputDecoration
    -0.83
     становника
    -0.82
    +#+
    -0.82
     ―――――
    -0.81
     doubtnut
    -0.79
     мәкал
    -0.79
    POSITIVE LOGITS
     مباشرة
    0.75
     near
    0.61
     in
    0.59
     towards
    0.59
     close
    0.57
     toward
    0.56
     where
    0.55
     closest
    0.54
    ,
    0.54
    near
    0.52
    Activations Density 0.343%

    No Known Activations