© 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. 3-GEMMASCOPE-RES-16K
    11. 5476
    Prev
    Next
    INDEX
    Explanations

    the concept of exclusivity or exclusive access

    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
    MigrationBuilder
    -0.78
    modb
    -0.72
    yargs
    -0.67
    nezeu
    -0.66
    odils
    -0.66
    *}$
    -0.65
    enoord
    -0.65
    SBATCH
    -0.65
    SharedDtor
    -0.65
     onData
    -0.63
    POSITIVE LOGITS
     exclusive
    3.17
     Exclusive
    2.95
    Exclusive
    2.88
    exclusive
    2.86
     EXCLUSIVE
    2.63
    EXCLUSIVE
    2.50
     Exclu
    2.45
     exclusives
    2.33
    Exclu
    2.28
     exclu
    2.27
    Activations Density 0.088%

    No Known Activations