© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10515
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between entities or concepts

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

    that often follow "and"

    np_acts-logits-general · gemini-2.0-flash

    loss, emergence, defense, using, customs, pharmaceutical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dovre
    -0.30
     hver
    -0.29
    Statics
    -0.28
     joka
    -0.27
     vrou
    -0.26
     души
    -0.26
     fiecare
    -0.26
     correctamente
    -0.26
     chẳng
    -0.26
     hvert
    -0.25
    POSITIVE LOGITS
     typelib
    0.85
     willingness
    0.79
     inability
    0.79
    การ
    0.75
    RegressionTest
    0.74
     lack
    0.73
     insistence
    0.71
     отсутствие
    0.71
     consequent
    0.71
     наличие
    0.69
    Activations Density 0.603%

    No Known Activations