© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11542
    Prev
    Next
    INDEX
    Explanations

    descriptive features of characters, particularly focusing on physical attributes and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.67
    Хьажоргаш
    -0.57
    ThroughAttribute
    -0.54
    gonic
    -0.54
    prelude
    -0.51
    tetés
    -0.50
    edale
    -0.50
    รุ่น
    -0.49
    felves
    -0.49
     doInBackground
    -0.49
    POSITIVE LOGITS
     personality
    0.95
     charisma
    0.89
     looks
    0.82
     physique
    0.72
     demeanor
    0.72
     manners
    0.70
    personality
    0.69
     smile
    0.67
     personalidad
    0.67
     charm
    0.67
    Activations Density 0.277%

    No Known Activations