© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    references to protocols

    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
     Efq
    -0.84
     Theſe
    -0.80
    GeneratedValue
    -0.79
    ecirc
    -0.71
     Sight
    -0.69
     seat
    -0.68
     Sre
    -0.68
    SQLiteDatabase
    -0.66
     يتيمه
    -0.66
     dirt
    -0.66
    POSITIVE LOGITS
     protocol
    3.09
     Protocol
    2.89
     protocols
    2.87
    Protocol
    2.64
    protocol
    2.63
     Protocols
    2.50
     PROTOCOL
    2.49
     protocolo
    2.27
    Protocols
    2.19
    PROTOCOL
    2.12
    Activations Density 0.062%

    No Known Activations