© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 137
    Prev
    Next
    INDEX
    Explanations

    expressions of personal beliefs and thoughts

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

    "I think" statements

    np_acts-logits-general · gemini-2.0-flash

    i think

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Efq
    -1.04
    ſelf
    -1.03
    ſelves
    -0.94
     Jefus
    -0.89
     Majefty
    -0.87
     Diſ
    -0.80
     poffible
    -0.78
     itſelf
    -0.78
     Houſe
    -0.77
     Reſ
    -0.77
    POSITIVE LOGITS
     it
    1.06
     we
    0.81
     this
    0.78
     there
    0.69
     maybe
    0.67
     you
    0.66
     the
    0.64
     thats
    0.64
     most
    0.62
     that
    0.61
    Activations Density 0.112%

    No Known Activations