© 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. 20-GEMMASCOPE-RES-16K
    11. 904
    Prev
    Next
    INDEX
    Explanations

    attributes and qualities of individuals, particularly in the context of performance and interpersonal skills

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

    Positive personal qualities or skills

    np_acts-logits-general · gemini-2.0-flash

    qualities and skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.86
    ThroughAttribute
    -0.85
    astify
    -0.79
    onAttach
    -0.72
     Réponses
    -0.70
    SceneManagement
    -0.70
    ########.
    -0.70
    adaptiveStyles
    -0.68
    SBATCH
    -0.68
     doInBackground
    -0.68
    POSITIVE LOGITS
     ability
    1.08
     sense
    1.02
     personality
    0.97
     skills
    0.95
     charisma
    0.92
     knack
    0.91
     skill
    0.85
     talents
    0.84
     humor
    0.81
     abilities
    0.80
    Activations Density 0.229%

    No Known Activations