© 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. 33-GEMMASCOPE-RES-16K
    11. 8575
    Prev
    Next
    INDEX
    Explanations

    expressions of ambition and potential in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cluye
    -0.44
    どうしても
    -0.44
    Losing
    -0.42
     perder
    -0.42
    dispon
    -0.41
     losing
    -0.40
     vouloir
    -0.39
     lose
    -0.39
    tabolism
    -0.39
     precisar
    -0.38
    POSITIVE LOGITS
     compete
    0.90
     competing
    0.85
     contending
    0.83
     competes
    0.82
     contention
    0.75
     contend
    0.74
     contender
    0.73
     rival
    0.65
     competed
    0.63
     vying
    0.63
    Activations Density 0.243%

    No Known Activations