© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6921
    Prev
    Next
    INDEX
    Explanations

    references to skills and competencies in educational or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reiche
    -0.45
     Monteiro
    -0.44
     Carrington
    -0.43
     Leighton
    -0.42
     reports
    -0.41
     BoxDecoration
    -0.41
     Berge
    -0.38
    })),
    -0.38
     report
    -0.38
    
    -0.38
    POSITIVE LOGITS
     skills
    1.74
     Skills
    1.73
     Skill
    1.70
    skills
    1.68
    Skills
    1.68
     skill
    1.67
    Skill
    1.63
    skill
    1.52
     SKILLS
    1.50
    SKILL
    1.29
    Activations Density 0.128%

    No Known Activations