© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2162
    Prev
    Next
    INDEX
    Explanations

    mentions of private entities or concepts related to privacy

    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
    évaluateur
    -0.82
     duquel
    -0.76
    FormTagHelper
    -0.73
     ThemeData
    -0.70
    GEBURTS
    -0.70
     onOptions
    -0.69
     skaters
    -0.69
    {}{}
    -0.68
     souha
    -0.68
    athletes
    -0.67
    POSITIVE LOGITS
     private
    2.93
     Private
    2.71
    Private
    2.66
     PRIVATE
    2.45
    PRIVATE
    2.33
     privately
    2.16
    private
    2.09
     privaten
    2.01
     privada
    2.01
     privé
    1.95
    Activations Density 0.046%

    No Known Activations