© 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. 24-GEMMASCOPE-RES-16K
    11. 1922
    Prev
    Next
    INDEX
    Explanations

    statements and inquiries about causality and evidence

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

    "he" after certain words

    np_acts-logits-general · gemini-2.0-flash

    pronoun he

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    His
    -1.17
     his
    -1.05
    his
    -1.04
     His
    -0.96
     seinen
    -0.90
    HIS
    -0.84
     HIS
    -0.82
     hans
    -0.76
     seine
    -0.75
     istrinya
    -0.70
    POSITIVE LOGITS
     he
    3.29
    he
    1.72
     он
    1.72
    He
    1.28
     HE
    1.27
     він
    1.25
     הוא
    1.15
     वह
    1.07
     He
    0.99
     hee
    0.95
    Activations Density 0.541%

    No Known Activations