© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9364
    Prev
    Next
    INDEX
    Explanations

    references to systemic injustice and racial disparities

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

    Sarcasm or disbelief markers

    np_acts-logits-general · gemini-2.0-flash

    supposedly or allegedly true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌آمباردا
    -0.63
    '])->
    -0.57
     дописавши
    -0.56
    <eos>
    -0.54
    انجليز
    -0.54
     disponibilités
    -0.53
    揄
    -0.51
    :"-"`
    -0.50
    ())));
    -0.49
    [@
    -0.48
    POSITIVE LOGITS
     somehow
    1.04
     яко
    0.97
     supuestamente
    0.89
     angeb
    0.83
     supposedly
    0.81
     magically
    0.81
     allegedly
    0.70
     onOptions
    0.69
     colpa
    0.68
     Somehow
    0.68
    Activations Density 0.766%

    No Known Activations