© 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. 24-GEMMASCOPE-RES-16K
    11. 159
    Prev
    Next
    INDEX
    Explanations

    patterns related to competition and selection processes

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

    Identifying superlatives and winners

    np_acts-logits-general · gemini-2.0-flash

    winner or candidate selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.54
     IBOutlet
    -0.54
    httphttps
    -0.46
    featureID
    -0.45
     forState
    -0.43
     EdgeInsets
    -0.40
    NameInMap
    -0.40
    
    -0.40
     Signalez
    -0.39
     Numerade
    -0.39
    POSITIVE LOGITS
     best
    0.66
     whichever
    0.63
    best
    0.58
     closest
    0.54
     lowest
    0.54
    closest
    0.54
     nearest
    0.52
    最
    0.51
     fastest
    0.50
     strongest
    0.50
    Activations Density 0.400%

    No Known Activations