© 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. 18-GEMMASCOPE-RES-16K
    11. 297
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotional expressions or charismatic personalities, particularly in the context of leadership

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

    excitement and energy

    np_acts-logits-general · gemini-2.0-flash

    energy and excitement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     silêncio
    -0.61
     SIMBAD
    -0.59
     quiet
    -0.59
     Quiet
    -0.59
     halus
    -0.57
    地味
    -0.57
    Quiet
    -0.55
    Peaceful
    -0.55
     []:
    -0.54
     :'(
    -0.54
    POSITIVE LOGITS
     energetic
    1.16
     energ
    1.13
     excitement
    1.11
     adrenaline
    1.11
     exuberant
    1.07
     energized
    1.05
     exuber
    1.04
     enthusiasm
    1.02
     enthusiastic
    0.96
    energ
    0.94
    Activations Density 0.350%

    No Known Activations