© 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. 19-GEMMASCOPE-RES-16K
    11. 3656
    Prev
    Next
    INDEX
    Explanations

    references to "assumptions" and variations of that concept, often in a technical or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enerys
    -0.62
    hedral
    -0.58
    IService
    -0.57
     Temples
    -0.55
    ruptedException
    -0.55
    Ferdin
    -0.55
    Tru
    -0.54
     GenerationType
    -0.53
     upra
    -0.53
    Redirection
    -0.53
    POSITIVE LOGITS
     ASS
    0.79
     Assets
    0.74
    клопе
    0.73
     asse
    0.70
    ASS
    0.70
    ConstraintMaker
    0.70
    ASSET
    0.69
     assets
    0.68
     ASSETS
    0.65
    Assets
    0.65
    Activations Density 0.210%

    No Known Activations