© 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. 3-GEMMASCOPE-RES-16K
    11. 9883
    Prev
    Next
    INDEX
    Explanations

    directional or positional phrases that suggest movement or escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alſo
    -0.52
     juſt
    -0.52
     uſed
    -0.51
     firſt
    -0.51
     auffi
    -0.51
     ſur
    -0.47
     faſt
    -0.47
     whoſe
    -0.47
     chiaro
    -0.47
     Eſ
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.84
    LookAnd
    0.76
    
    0.74
     autorytatywna
    0.73
    migrationBuilder
    0.70
     kasarigan
    0.70
     Biôgrafia
    0.70
    存于互联网档案馆
    0.69
    帖最后由
    0.68
    Jeografia
    0.66
    Activations Density 0.162%

    No Known Activations