© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10878
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and safety culture in professional settings

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

    quality improvement methodologies

    np_acts-logits-general · gemini-2.0-flash

    lean improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.70
    ThroughAttribute
    -0.54
    ExecuteReader
    -0.53
    FileChooser
    -0.52
     Connectez
    -0.52
    FirebaseAuth
    -0.52
    erapeu
    -0.50
    ophys
    -0.49
    putin
    -0.48
     VizieR
    -0.48
    POSITIVE LOGITS
     Lean
    1.02
     improvement
    0.92
    Lean
    0.90
     lean
    0.88
    LEAN
    0.83
    improvement
    0.81
     Improvement
    0.80
     ISO
    0.79
    amélioration
    0.78
    Improvement
    0.78
    Activations Density 0.183%

    No Known Activations