© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    locations and place names

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

    locations

    np_acts-logits-general · gemini-2.0-flash

    place names and districts

    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
    ContentAsync
    -0.74
     InputDecoration
    -0.72
    onomian
    -0.71
     Obrador
    -0.69
     GetEnumerator
    -0.69
     VizieR
    -0.65
     ModelExpression
    -0.63
     }}$}
    -0.63
    findpost
    -0.63
    }$}
    -0.62
    POSITIVE LOGITS
     village
    0.91
     Village
    0.77
    village
    0.70
    Village
    0.64
     district
    0.62
     near
    0.61
     neighbourhood
    0.60
     neighborhood
    0.60
     resident
    0.57
     station
    0.56
    Activations Density 0.185%

    No Known Activations