© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1208
    Prev
    Next
    INDEX
    Explanations

    instances of significant financial outcomes or events related to winnings

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

    a male person

    np_acts-logits-general · gemini-2.0-flash

    he, him, his, himself

    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
     &=&
    -0.70
    &=&\
    -0.59
    她們
    -0.59
    &=&
    -0.58
     fallu
    -0.57
    它们
    -0.55
    它們
    -0.55
     которое
    -0.54
     करती
    -0.54
     Оно
    -0.54
    POSITIVE LOGITS
     his
    3.89
     he
    3.09
     him
    3.07
    his
    2.96
     himself
    2.88
    彼は
    2.79
    彼の
    2.78
    彼が
    2.63
    himself
    2.38
    他的
    2.35
    Activations Density 6.151%

    No Known Activations