© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10191
    Prev
    Next
    INDEX
    Explanations

    terms related to systems and systematic approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.92
    sizeCache
    -0.86
     ſeveral
    -0.81
    sidemargin
    -0.78
    CreateMap
    -0.78
     Efq
    -0.75
     Jefus
    -0.71
     himſelf
    -0.71
     Chrift
    -0.70
     Monfieur
    -0.69
    POSITIVE LOGITS
     systems
    1.21
     Systems
    1.04
     SYSTEMS
    0.97
    atics
    0.92
    wide
    0.92
    atically
    0.91
    systems
    0.90
     system
    0.88
    Systems
    0.87
    ically
    0.84
    Activations Density 0.122%

    No Known Activations