© 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. 33-GEMMASCOPE-RES-16K
    11. 11490
    Prev
    Next
    INDEX
    Explanations

    contexts involving personal connections and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seen
    -0.57
     referrerpolicy
    -0.56
     Seen
    -0.50
     awareness
    -0.46
     seen
    -0.45
    rrggbb
    -0.45
    Seen
    -0.44
     conscientes
    -0.43
     Villiers
    -0.42
    LEncoder
    -0.41
    POSITIVE LOGITS
     know
    1.00
    Know
    0.85
     Know
    0.85
    know
    0.81
     kennen
    0.72
    KNOW
    0.72
     conhecer
    0.69
     conocen
    0.66
     conocer
    0.65
     KNOW
    0.65
    Activations Density 0.257%

    No Known Activations