© 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. 10146
    Prev
    Next
    INDEX
    Explanations

    complex technical descriptions related to semiconductor processes and modifications

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    causes, consequences, explanations, requirements

    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
     noDo
    -0.64
     étoit
    -0.58
     насељу
    -0.54
    DockStyle
    -0.50
     alphabetically
    -0.49
     networked
    -0.49
     girlfriends
    -0.48
     kids
    -0.48
     narcis
    -0.48
     autorytatywna
    -0.47
    POSITIVE LOGITS
     sufficient
    0.52
    verifyException
    0.49
     ausreich
    0.47
     penting
    0.46
     mejora
    0.44
     modifikasi
    0.44
     Verbesserung
    0.43
     utilización
    0.42
     Wikiseite
    0.42
     erforder
    0.40
    Activations Density 3.757%

    No Known Activations