© 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. 22-GEMMASCOPE-RES-16K
    11. 3121
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or doubt

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

    preceding "sure" or related to certainty

    np_acts-logits-general · gemini-2.0-flash

    not sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrWhiteSpace
    -0.63
     AssemblyTitle
    -0.56
    Datuak
    -0.56
    TestingModule
    -0.55
    RenderAtEndOf
    -0.52
    ябре
    -0.51
     ویکی‌آمباردا
    -0.50
    Kariera
    -0.49
    Jegyzetek
    -0.49
    Gizmos
    -0.48
    POSITIVE LOGITS
     sure
    2.50
    sure
    2.11
     SURE
    2.00
    Sure
    1.84
     Sure
    1.78
     certainty
    1.75
     sûr
    1.58
     assured
    1.51
     sicher
    1.49
     certeza
    1.48
    Activations Density 0.193%

    No Known Activations