© 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. 10686
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" and expressions of personal perspective or opinion

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

    First-person conditional statements

    np_acts-logits-general · gemini-2.0-flash

    I would hypothetical examples

    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
     gonna
    -0.82
     likely
    -0.78
     Should
    -0.75
     Gonna
    -0.74
     Was
    -0.74
     Were
    -0.73
     GONNA
    -0.72
     Has
    -0.72
     Would
    -0.72
     Did
    -0.70
    POSITIVE LOGITS
     للمعارف
    0.98
     AssemblyCulture
    0.95
    tagHelperRunner
    0.95
     myſelf
    0.94
     الرياضيه
    0.94
     itſelf
    0.91
    tvguidetime
    0.90
     kasarigan
    0.90
     الحره
    0.89
     للاسماء
    0.88
    Activations Density 0.178%

    No Known Activations