© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10467
    Prev
    Next
    INDEX
    Explanations

    verbs indicative of actions and changes in state

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

    Verbs describing actions done to oneself or others

    np_acts-logits-general · gemini-2.0-flash

    specific language markers

    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
     principale
    -0.39
     forstå
    -0.37
     principaux
    -0.36
     principal
    -0.36
     senhor
    -0.35
     bestemt
    -0.35
     aanbied
    -0.35
     during
    -0.34
     sebenarnya
    -0.34
     działania
    -0.34
    POSITIVE LOGITS
     betweenstory
    0.79
     мәкал
    0.73
    GEBURTSDATUM
    0.72
     дописавши
    0.71
    تقاوى
    0.70
    səhifə
    0.70
    Портали
    0.69
    GEBURTS
    0.69
     виправивши
    0.66
    ðsíða
    0.66
    Activations Density 0.799%

    No Known Activations