© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13548
    Prev
    Next
    INDEX
    Explanations

    phrases expressing actions and commands related to decision-making or inquiries

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

    Statements of discovery or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    discovery and resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     ſch
    -0.47
     tiden
    -0.46
     jorden
    -0.46
     dahulu
    -0.43
     ilustracja
    -0.43
     suaminya
    -0.43
     Universitaria
    -0.42
     Masyarakat
    -0.42
     rumahnya
    -0.41
     nothwendig
    -0.41
    POSITIVE LOGITS
     nahilalakip
    0.69
     lenker
    0.67
    Життєпис
    0.65
    httphttps
    0.58
    ंदीखरीदारी
    0.54
    CrossRef
    0.51
     gotta
    0.51
     gonna
    0.50
    ArrowToggle
    0.50
    BindView
    0.50
    Activations Density 0.453%

    No Known Activations