© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 189
    Prev
    Next
    INDEX
    Explanations

    offer negotiations and competitive job scenarios

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

    competing offers, bidding war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     الوطنيه
    -0.46
     JpaRepository
    -0.45
    protoc
    -0.45
    isbol
    -0.43
    chemy
    -0.43
    upol
    -0.43
    TargetException
    -0.43
     Sanger
    -0.43
     étoient
    -0.42
     avoient
    -0.42
    POSITIVE LOGITS
     counter
    0.96
     competing
    0.93
     countered
    0.91
     rival
    0.88
     competition
    0.86
     compete
    0.85
     competitive
    0.83
     competes
    0.80
     competitor
    0.77
     competitors
    0.74
    Activations Density 0.078%

    No Known Activations