© 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. 7278
    Prev
    Next
    INDEX
    Explanations

    expressions of human desires and intentions

    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
     INTERESAR
    -0.54
     >=",
    -0.47
     whereby
    -0.47
     mivel
    -0.43
     ResourceManager
    -0.43
    หว่าง
    -0.43
     ведь
    -0.42
    حيث
    -0.42
     sachant
    -0.41
     paralelo
    -0.41
    POSITIVE LOGITS
    -------------</
    0.79
     duh
    0.76
     literalmente
    0.76
    RetentionPolicy
    0.75
    duh
    0.73
    Literally
    0.73
     Literally
    0.72
     muualla
    0.70
    LEncoder
    0.68
    literally
    0.68
    Activations Density 0.262%

    No Known Activations