© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15380
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and locational descriptors within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.67
    NUMX
    -0.59
     незавершена
    -0.59
    findpost
    -0.59
     BNF
    -0.58
     Voltaire
    -0.56
     
    -0.54
     noastre
    -0.54
    ſelf
    -0.54
     meriva
    -0.54
    POSITIVE LOGITS
     beneath
    0.94
     behind
    0.90
     derrière
    0.90
    Beneath
    0.88
     Beneath
    0.87
     underneath
    0.84
    Behind
    0.79
     debajo
    0.78
     Behind
    0.78
     davanti
    0.77
    Activations Density 0.268%

    No Known Activations