© 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. 11340
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate personal pronouns and their interactions in sentences

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

    Preceding pronouns or names

    np_acts-logits-general · gemini-2.0-flash

    attributing things to someone

    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
     reasoning
    -0.58
     Reasoning
    -0.54
     собі
    -0.50
    を受けた
    -0.49
    を受けて
    -0.48
     JpaRepository
    -0.46
     betrokken
    -0.46
     mukana
    -0.46
    得到了
    -0.45
     sobie
    -0.44
    POSITIVE LOGITS
     owe
    0.65
     Paglinawan
    0.62
    ########.
    0.61
     assigned
    0.61
     belonged
    0.60
     belongs
    0.60
     belong
    0.59
     owes
    0.58
     dedicate
    0.58
     ascribed
    0.58
    Activations Density 0.063%

    No Known Activations