© 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 - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 5576
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between ideas or entities

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

    adjectives after lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puisqu
    -0.25
     biến
    -0.25
     reclamo
    -0.24
     exclusivement
    -0.24
     fragmentation
    -0.23
    érité
    -0.23
     umgekehrt
    -0.23
     tổng
    -0.23
     es
    -0.23
     parades
    -0.22
    POSITIVE LOGITS
     wonderful
    0.98
     amazing
    0.90
     lovely
    0.90
     beautiful
    0.87
    wonderful
    0.87
    ConstraintMaker
    0.86
     awesome
    0.85
     interesting
    0.85
     nice
    0.83
     yummy
    0.83
    Activations Density 0.035%

    No Known Activations