© 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. 35-GEMMASCOPE-RES-16K
    11. 11083
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns related to personal empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colgroup
    -0.47
     мәкал
    -0.45
    SharedDtor
    -0.44
     nahilalakip
    -0.41
    abestanden
    -0.41
    awtextra
    -0.39
     المعيارى
    -0.38
    Datuak
    -0.36
    SerializedName
    -0.34
     @"/
    -0.34
    POSITIVE LOGITS
     pleases
    1.09
     please
    1.00
     pleased
    0.94
     liking
    0.93
     pleasure
    0.91
     wish
    0.89
     wishes
    0.84
    please
    0.82
     whim
    0.79
     desires
    0.79
    Activations Density 0.314%

    No Known Activations