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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12620
    Prev
    Next
    INDEX
    Explanations

    references to geometric shapes and lattice structures in materials science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    Personensuche
    -0.59
    errHandler
    -0.56
     mapStateToProps
    -0.54
     Gra
    -0.54
     Du
    -0.53
    IVEREF
    -0.52
    onViewCreated
    -0.52
     ComVisible
    -0.51
    potranspiration
    -0.51
    POSITIVE LOGITS
     cube
    1.08
     Cube
    1.02
     cubes
    1.02
    cube
    1.01
    CUBE
    0.97
    Cube
    0.97
     Cubes
    0.93
     squares
    0.89
     square
    0.87
     Sphere
    0.86
    Activations Density 1.110%

    No Known Activations