© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15820
    Prev
    Next
    INDEX
    Explanations

    statements made by officials or ministers regarding announcements and cooperation efforts

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

    direct quotes attributed to specific named individuals.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     tatsächlich
    -0.41
     ajuns
    -0.39
     ohnehin
    -0.38
     arşivlendi
    -0.38
     doká
    -0.37
     Chwiliwch
    -0.36
    jooq
    -0.36
     ľah
    -0.35
     onCreateView
    -0.35
    Rüyada
    -0.34
    POSITIVE LOGITS
     whilst
    0.57
    
    0.56
     disclosed
    0.55
     while
    0.54
     Whilst
    0.53
     Emphas
    0.52
     stated
    0.50
     stressed
    0.50
     further
    0.49
     however
    0.49
    Activations Density 0.080%

    No Known Activations