© 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. 10189
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "you"

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

    "You can" or "I can" phrases

    np_acts-logits-general · gemini-2.0-flash

    you can / could

    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
     ability
    -0.90
    Ability
    -0.77
    ability
    -0.76
     Ability
    -0.74
     able
    -0.66
     abilities
    -0.59
     capable
    -0.59
    Able
    -0.59
     capability
    -0.58
    SharedCtor
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.82
    mybatisplus
    0.81
     BorderRadius
    0.78
     ModelExpression
    0.72
    TagMode
    0.70
    ChromeDriver
    0.70
     ivelany
    0.69
    tagHelperRunner
    0.68
    AddHtmlAttribute
    0.65
    zzleHttp
    0.63
    Activations Density 0.098%

    No Known Activations