© 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. 20-GEMMASCOPE-RES-16K
    6. 5996
    Prev
    Next
    INDEX
    Explanations

    references to various skills and competencies necessary for effective performance in different areas

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

    words related to professional skills and capabilities.

    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
     bericht
    -0.40
     report
    -0.40
     reports
    -0.40
     Nath
    -0.39
     berichten
    -0.39
     Lath
    -0.39
     Pugh
    -0.38
     Monteiro
    -0.38
     big
    -0.38
     Report
    -0.37
    POSITIVE LOGITS
     Skill
    1.23
    Skill
    1.20
     skill
    1.15
     Skills
    1.14
     skills
    1.13
    Skills
    1.13
    skills
    1.08
    skill
    1.05
     SKILLS
    1.01
    SKILL
    1.00
    Activations Density 0.043%

    No Known Activations