© 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. 19-GEMMASCOPE-RES-16K
    11. 8158
    Prev
    Next
    INDEX
    Explanations

    references to beds and sleeping arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áculo
    -0.48
    UObject
    -0.43
    dams
    -0.43
    jería
    -0.41
    sieke
    -0.41
     permiso
    -0.41
    Subnet
    -0.40
     ganglia
    -0.38
     delegación
    -0.38
     домо
    -0.38
    POSITIVE LOGITS
     bed
    2.41
     beds
    2.07
     BED
    1.92
     Bed
    1.90
    Bed
    1.88
    bed
    1.87
     Beds
    1.82
    beds
    1.69
    Beds
    1.66
    BED
    1.61
    Activations Density 0.088%

    No Known Activations