© 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. 15368
    Prev
    Next
    INDEX
    Explanations

    elements related to quality, clarity, and efficiency in communication or presentation

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

    after "of" relating to quality/accuracy

    np_acts-logits-general · gemini-2.0-flash

    qualities and attributes

    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
     législation
    -0.59
     réglementation
    -0.53
    windowFixed
    -0.52
     refroid
    -0.50
    godic
    -0.49
     malheure
    -0.49
     tärke
    -0.48
     nî
    -0.48
     viktigt
    -0.47
     aján
    -0.46
    POSITIVE LOGITS
     accuracy
    1.65
     simplicity
    1.52
     reliability
    1.50
     completeness
    1.50
     stability
    1.49
     efficiency
    1.49
     flexibility
    1.47
     robustness
    1.47
     effectiveness
    1.46
     authenticity
    1.45
    Activations Density 2.164%

    No Known Activations