© 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. 25-GEMMASCOPE-RES-16K
    11. 15042
    Prev
    Next
    INDEX
    Explanations

    queries or expressions of frustration related to finding or troubleshooting items or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pautan
    -0.47
    domada
    -0.43
     indeb
    -0.39
    tráfico
    -0.39
    Hentet
    -0.36
    assemble
    -0.36
     purpoſe
    -0.35
     noblesse
    -0.35
     ujednoznacz
    -0.35
    ]!='
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.63
     frustrated
    0.61
     Frust
    0.60
     desperation
    0.60
    Frust
    0.59
     despair
    0.59
    諦
    0.58
     frustrating
    0.57
     dejected
    0.56
    frust
    0.56
    Activations Density 0.509%

    No Known Activations