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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 14839
    Prev
    Next
    INDEX
    Explanations

    referenced pronouns, particularly the first-person singular "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    um
    -0.58
    ide
    -0.58
    an
    -0.57
    ha
    -0.56
    ah
    -0.55
    el
    -0.55
    en
    -0.55
    s
    -0.54
    et
    -0.54
    ar
    -0.54
    POSITIVE LOGITS
     i
    1.19
    parsedMessage
    0.79
     ii
    0.69
     kaarangay
    0.67
    aarrggbb
    0.63
    rungsseite
    0.61
     iii
    0.60
     SwitchCompat
    0.60
    oredCriteria
    0.60
     ویکی‌پدی
    0.59
    Activations Density 0.541%

    No Known Activations