© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    thematic elements related to social critique and political commentary

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

    Follows a contrasting conjunction

    np_acts-logits-general · gemini-2.0-flash

    but, perhaps, yet

    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
     welches
    -0.80
     Anyways
    -0.78
     للمعارف
    -0.76
    />";
    -0.76
    featureID
    -0.72
     Utilize
    -0.70
     seperate
    -0.69
     dirinya
    -0.67
    кож
    -0.66
    ])){
    -0.65
    POSITIVE LOGITS
     freilich
    0.97
     doubtless
    0.78
     jedenfalls
    0.73
     nė
    0.67
     such
    0.66
    それにしても
    0.66
     persino
    0.65
     readers
    0.64
     none
    0.63
     manifestly
    0.63
    Activations Density 0.595%

    No Known Activations