© 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. 18-GEMMASCOPE-RES-16K
    11. 11679
    Prev
    Next
    INDEX
    Explanations

    discussions of behaviors and attributes relating to subjects like amber, politics, and societal stereotypes

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

    following "how"

    np_acts-logits-general · gemini-2.0-flash

    questions about how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.54
    bulin
    -0.49
     дописавши
    -0.49
    ValueGeneration
    -0.47
    orn
    -0.46
    DoubleQuotes
    -0.46
    réhen
    -0.46
     disponibilités
    -0.46
    ಿನ
    -0.46
    Quite
    -0.46
    POSITIVE LOGITS
     somehow
    1.35
     яко
    1.18
     magically
    1.09
     supuestamente
    1.07
     supposedly
    1.03
     angeb
    1.01
     Somehow
    0.87
    Somehow
    0.83
     müsse
    0.78
     allegedly
    0.78
    Activations Density 0.941%

    No Known Activations