© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2565
    Prev
    Next
    INDEX
    Explanations

    numerical data or values, particularly in contexts related to statistical or mathematical analysis

    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
     épaules
    -0.60
     Sekund
    -0.59
     varandra
    -0.57
     copertina
    -0.52
     thịt
    -0.52
     jedin
    -0.51
     tromper
    -0.50
     tjen
    -0.50
     reflejo
    -0.50
     motivo
    -0.50
    POSITIVE LOGITS
    ModelSerializer
    1.00
     MainAxisSize
    0.83
     himo
    0.80
     ModelExpression
    0.76
    CloseOperation
    0.75
    Personendaten
    0.75
     تضيفلها
    0.71
     StringField
    0.67
    AnimationsModule
    0.67
    stdbool
    0.66
    Activations Density 0.287%

    No Known Activations