© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 16101
    Prev
    Next
    INDEX
    Explanations

    details about personal characteristics and attributes of individuals, particularly relating to their humor, dedication, and interpersonal skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afficheront
    -0.58
    IBOutlet
    -0.56
    PyExc
    -0.55
     propOrder
    -0.55
    felves
    -0.54
    ArgumentParser
    -0.52
    ViewImports
    -0.50
    RepeatedField
    -0.49
     calculées
    -0.49
    avro
    -0.48
    POSITIVE LOGITS
     contagious
    0.84
     infectious
    0.83
     energy
    0.73
     humor
    0.72
     warmth
    0.71
     charisma
    0.70
     positivity
    0.69
     personality
    0.69
     wit
    0.68
     charm
    0.68
    Activations Density 0.212%

    No Known Activations