© 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. 28-GEMMASCOPE-RES-16K
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    references to purchasing and financial transactions involving specific items

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

    after "and", "a", "has", "benefits"

    np_acts-logits-general · gemini-2.0-flash

    cost and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.38
    __;
    -0.32
    :✨
    -0.31
    })}\
    -0.31
    vatie
    -0.29
    encre
    -0.29
     pieles
    -0.28
     thự
    -0.28
     leksikon
    -0.28
    urtstag
    -0.27
    POSITIVE LOGITS
     cost
    2.34
     costs
    2.27
     costing
    2.13
    cost
    2.03
     priced
    2.00
     Cost
    1.98
     Costs
    1.95
     price
    1.95
    Cost
    1.93
    costs
    1.91
    Activations Density 0.969%

    No Known Activations