© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or requests for clarification

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

    Followed by personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    first person claims

    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
     StatefulWidget
    -0.75
    RenderAtEndOf
    -0.71
     Eure
    -0.71
     Anſ
    -0.71
     Majefty
    -0.71
    ſelf
    -0.68
     itſelf
    -0.67
    ніципа
    -0.67
     ModelExpression
    -0.67
     Monfieur
    -0.66
    POSITIVE LOGITS
     me
    1.53
     my
    1.45
     conmigo
    1.42
     мной
    1.19
     comigo
    1.10
     моих
    1.03
     I
    1.01
     meines
    0.99
     mijn
    0.99
     mnie
    0.97
    Activations Density 0.259%

    No Known Activations