© 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. 5398
    Prev
    Next
    INDEX
    Explanations

    phrases related to rewards and incentives within a payment structure

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

    Preceding "by" (often related to payment or calculation)

    np_acts-logits-general · gemini-2.0-flash

    by paying

    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
     fijo
    -0.36
     confiable
    -0.35
     snippetHide
    -0.33
     inclusión
    -0.33
     universidad
    -0.32
     amado
    -0.32
     posibil
    -0.32
     autoridad
    -0.31
     mulig
    -0.31
     möj
    -0.30
    POSITIVE LOGITS
     nakalista
    0.74
    /**
    0.63
    oredCriteria
    0.58
     successfully
    0.58
    Aholisi
    0.56
    Sklici
    0.56
    ImageContext
    0.54
    Әдәбият
    0.54
    Filmo
    0.54
     successful
    0.53
    Activations Density 0.294%

    No Known Activations