© 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. 24-GEMMASCOPE-RES-16K
    11. 14690
    Prev
    Next
    INDEX
    Explanations

    tones of humor and charm in interactions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive personality traits

    np_acts-logits-general · gemini-2.0-flash

    positive personality traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    felves
    -0.69
    WithIOException
    -0.60
    ArgumentParser
    -0.56
    Mistake
    -0.53
    regierung
    -0.52
    aarrggbb
    -0.52
     mahdollis
    -0.51
     subgoal
    -0.50
     paž
    -0.50
    IBOutlet
    -0.49
    POSITIVE LOGITS
     charisma
    0.96
     personality
    0.94
     charm
    0.93
     warmth
    0.82
     infectious
    0.81
     presence
    0.78
     wit
    0.77
    personality
    0.76
     personnalité
    0.75
     personalidad
    0.75
    Activations Density 0.153%

    No Known Activations