© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108157
    Prev
    Next
    INDEX
    Explanations

    references to professionalism and skilled professionals

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

    professional occupations and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     utwor
    -0.40
    RenderAtEndOf
    -0.36
     yyr
    -0.36
     goutte
    -0.35
    borderFill
    -0.35
     Building
    -0.34
     ultimi
    -0.34
     following
    -0.33
     ACCESS
    -0.33
    ridos
    -0.32
    POSITIVE LOGITS
    professional
    0.97
     professional
    0.92
    professionals
    0.89
     professionals
    0.87
    Professional
    0.85
     PROFESSIONAL
    0.84
     Professional
    0.82
    Profession
    0.80
    PROFESSIONAL
    0.79
    profession
    0.78
    Activations Density 0.008%

    No Known Activations