© 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. 3-GEMMASCOPE-RES-16K
    11. 1328
    Prev
    Next
    INDEX
    Explanations

    references to schemes in various 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
     Garry
    -0.65
    mort
    -0.63
     Overton
    -0.62
     EAT
    -0.62
     Luf
    -0.59
     Gallo
    -0.59
    fas
    -0.59
    !")
    -0.58
    eat
    -0.57
     Holden
    -0.56
    POSITIVE LOGITS
     scheme
    3.30
     Scheme
    3.19
    scheme
    3.18
     schemes
    3.12
    Scheme
    3.12
     SCHEME
    3.11
     Schemes
    3.08
    schemes
    2.87
    Schemes
    2.74
    SCHEME
    2.64
    Activations Density 0.068%

    No Known Activations