© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 10573
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openqa
    -0.37
    EReference
    -0.34
    saraba
    -0.32
    我觉得
    -0.31
    definitely
    -0.30
     userRepository
    -0.28
    ().__
    -0.28
    ttps
    -0.28
     minimum
    -0.27
    覺得
    -0.27
    POSITIVE LOGITS
     EconPapers
    0.98
    StoryboardSegue
    0.68
    XmlAccessType
    0.62
     confess
    0.60
     ویکی‌پدی
    0.59
     sospe
    0.59
     suspect
    0.58
    angliski
    0.57
     sosp
    0.56
     suspe
    0.54
    Activations Density 0.463%

    No Known Activations