© 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. 22-GEMMASCOPE-RES-16K
    11. 14675
    Prev
    Next
    INDEX
    Explanations

    punctuation marks such as quotation marks and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "Q:" or "Dependent"

    np_acts-logits-general · gemini-2.0-flash

    people and individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.77
    fromnode
    -0.69
     TextInputType
    -0.67
    .},
    -0.64
    ]}"
    -0.63
    Doch
    -0.63
    깥
    -0.63
    ))))))))
    -0.62
     gdyż
    -0.61
    需
    -0.60
    POSITIVE LOGITS
     everybody
    1.02
    Everybody
    0.97
     Everybody
    0.93
     somebody
    0.93
     basically
    0.89
     obviously
    0.89
     anybody
    0.87
     Somebody
    0.86
     you
    0.84
     I
    0.83
    Activations Density 0.188%

    No Known Activations