© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1789
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate experience and expertise in a specific field

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

    professional credentials and work experience, particularly multi-year experience in various fields.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    endphp
    -0.52
     defaultstate
    -0.48
    RefreshLayout
    -0.43
    putchar
    -0.42
    astify
    -0.41
     shut
    -0.40
     Pantheon
    -0.40
     Thing
    -0.39
    CLUS
    -0.38
    Externé
    -0.38
    POSITIVE LOGITS
     experience
    0.86
    Experience
    0.82
    Experienced
    0.82
     experienced
    0.82
    experienced
    0.81
     Experienced
    0.78
    EXPERIENCE
    0.78
     Experience
    0.77
    experience
    0.77
    经验
    0.75
    Activations Density 0.060%

    No Known Activations