© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 16306
    Prev
    Next
    INDEX
    Explanations

    automation and procedural texts, especially in the context of movement and orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semantics
    -0.60
     Schaefer
    -0.54
     prospect
    -0.54
     Cyber
    -0.54
     cyber
    -0.53
    ute
    -0.51
     moto
    -0.50
     ho
    -0.50
    又是
    -0.49
    fully
    -0.49
    POSITIVE LOGITS
    horizontal
    1.25
     Horizontal
    1.23
    Horizontal
    1.21
     horizontal
    1.19
     automatically
    1.08
     automatic
    1.05
     voluntary
    1.04
     Automatically
    1.01
    automatic
    1.01
    Automatic
    0.97
    Activations Density 0.106%

    No Known Activations