© 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. 9714
    Prev
    Next
    INDEX
    Explanations

    references to pistons and cylinders in mechanical engineering contexts

    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
     resourceCulture
    -0.61
    Eup
    -0.55
    fe
    -0.53
     Gesch
    -0.53
    esch
    -0.52
    Fe
    -0.52
    unch
    -0.52
     pos
    -0.52
     Broome
    -0.51
     direct
    -0.50
    POSITIVE LOGITS
     cylinder
    2.65
     cylinders
    2.57
     Cylinder
    2.42
    cylinder
    2.33
    Cylinder
    2.16
     Cyl
    1.98
     cilindro
    1.85
     cylind
    1.70
     cylindrical
    1.70
     cilindros
    1.67
    Activations Density 0.146%

    No Known Activations