© 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. 0-GEMMASCOPE-RES-16K
    11. 8209
    Prev
    Next
    INDEX
    Explanations

    concepts related to definitions or explanations of meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vats
    -0.44
     eff
    -0.42
     iprot
    -0.41
     succ
    -0.39
    fillType
    -0.39
    letta
    -0.39
     foul
    -0.38
    fflush
    -0.37
     rats
    -0.37
     apo
    -0.37
    POSITIVE LOGITS
    Meaning
    2.19
    meaning
    2.19
     meaning
    2.16
     Meaning
    2.13
     MEAN
    1.73
     meanings
    1.70
     Means
    1.62
    MEAN
    1.62
     significado
    1.60
     means
    1.57
    Activations Density 0.204%

    No Known Activations