© 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. 21-GEMMASCOPE-RES-16K
    11. 2447
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that present alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     etc
    -0.77
    etc
    -0.76
     noqa
    -0.76
    </caption>
    -0.72
     usw
    -0.72
    BagLayout
    -0.72
    InvalidProtocol
    -0.72
     betweenstory
    -0.70
    :]:
    -0.68
    varargin
    -0.68
    POSITIVE LOGITS
     alternatively
    1.12
    ,
    1.04
     alternately
    1.01
     equivalently
    0.98
     conversely
    0.96
     sometimes
    0.95
     perhaps
    0.94
     worse
    0.92
     indeed
    0.91
     maybe
    0.89
    Activations Density 0.286%

    No Known Activations