© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11975
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational competencies and skills development

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

    preceding "skills" or related terms

    np_acts-logits-general · gemini-2.0-flash

    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
    extAlignment
    -0.68
    InputBorder
    -0.60
     تضيفلها
    -0.54
     insp
    -0.53
    thalam
    -0.50
    Inspiration
    -0.50
    dolu
    -0.49
     accidents
    -0.49
    vää
    -0.48
    ParallelGroup
    -0.48
    POSITIVE LOGITS
     skills
    2.39
     skill
    2.02
    skills
    1.96
     Skills
    1.89
    Skills
    1.72
     SKILLS
    1.67
    skill
    1.66
     Skill
    1.58
    Skill
    1.55
     compétences
    1.44
    Activations Density 0.248%

    No Known Activations