© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7562
    Prev
    Next
    INDEX
    Explanations

    discussions about the value and quality of consumer goods, particularly in relation to pricing and production

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

    inexpensive or low-quality items

    np_acts-logits-general · gemini-2.0-flash

    cheap goods and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Carriera
    -0.62
    SuppressMessage
    -0.61
    omiast
    -0.57
     cương
    -0.57
    esity
    -0.55
    DataAnnotations
    -0.54
     الحره
    -0.51
     recommandée
    -0.48
    ItemBackground
    -0.48
     avancée
    -0.48
    POSITIVE LOGITS
     cheap
    1.99
     cheaply
    1.74
    cheap
    1.62
     cheaper
    1.60
    Cheap
    1.54
     inexpensive
    1.54
     Cheap
    1.49
     cheapest
    1.40
     деше
    1.30
     billig
    1.29
    Activations Density 0.328%

    No Known Activations