© 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. 1-GEMMASCOPE-RES-16K
    11. 6516
    Prev
    Next
    INDEX
    Explanations

    statistical models used in inference and regression analysis

    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
     ***!
    -0.66
     Orthop
    -0.63
    InSection
    -0.59
    NewGuid
    -0.57
    twimg
    -0.56
    telor
    -0.55
     tendenza
    -0.55
    فحة
    -0.55
    nosaurus
    -0.52
    racite
    -0.52
    POSITIVE LOGITS
     models
    1.25
     modeling
    1.20
     modelling
    1.18
     Models
    1.05
    Modeling
    1.03
     Modeling
    1.01
     Modelling
    0.97
    Modelling
    0.92
     MODELS
    0.91
    modeling
    0.86
    Activations Density 0.510%

    No Known Activations