© 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. 22-GEMMASCOPE-RES-16K
    11. 9355
    Prev
    Next
    INDEX
    Explanations

    instances of storytelling and personal anecdotes

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

    First-person anecdotes or stories

    np_acts-logits-general · gemini-2.0-flash

    i washe firstonce had

    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
     verder
    -0.76
    也都
    -0.69
    urther
    -0.65
     dále
    -0.64
     ulteriori
    -0.63
     AssemblyVersion
    -0.63
     continuer
    -0.62
    也就
    -0.60
     förstå
    -0.60
    themselves
    -0.60
    POSITIVE LOGITS
     accidentally
    1.09
     overheard
    1.07
     randomly
    0.75
     inadvertently
    0.71
     mistakenly
    0.70
    accident
    0.70
     asked
    0.69
    有一天
    0.68
     sitting
    0.66
     innocently
    0.65
    Activations Density 0.542%

    No Known Activations