© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    terms related to functionality and performance assessment 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
     mites
    -0.89
     StringTokenizer
    -0.83
    StoryboardSegue
    -0.82
     JSONException
    -0.81
     comets
    -0.81
    InSection
    -0.81
     CIE
    -0.80
     Hered
    -0.79
     palms
    -0.79
     leprosy
    -0.77
    POSITIVE LOGITS
     functional
    3.00
     Functional
    2.77
    Functional
    2.76
    functional
    2.68
     funcional
    2.18
     functionally
    1.87
     функциона
    1.85
     functionality
    1.73
     funcionales
    1.67
    Functionality
    1.46
    Activations Density 0.117%

    No Known Activations