© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 742
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy or contradictions in behavior or statements

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

    references to items, specifically boxed sets or collectible figures in a purchasing context

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

    exclamations and contradictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     especially
    -0.68
    especially
    -0.68
     Especially
    -0.67
    Especially
    -0.64
    談社
    -0.60
     szczególnie
    -0.60
    pecially
    -0.59
     FetchType
    -0.56
     especialmente
    -0.56
    either
    -0.56
    POSITIVE LOGITS
     (!)
    1.23
    (!)
    1.17
    ?!?!
    1.16
    !?!
    1.16
     apparently
    1.16
    ?!
    1.11
    Apparently
    1.10
     supuestamente
    1.09
     Apparently
    1.08
    apparently
    1.07
    Activations Density 0.287%

    No Known Activations