© 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. 18-GEMMASCOPE-RES-16K
    11. 9962
    Prev
    Next
    INDEX
    Explanations

    specific chemicals and their sources in experimental preparation

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

    Something was bought or obtained

    np_acts-logits-general · gemini-2.0-flash

    purchased or obtained from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considérons
    -0.51
     Occupancy
    -0.47
    ölker
    -0.46
    ophyll
    -0.46
    awtextra
    -0.45
    AlterField
    -0.45
    LLocation
    -0.44
    TagMode
    -0.44
     beginnetje
    -0.44
    वार
    -0.43
    POSITIVE LOGITS
     purchased
    1.66
     purchase
    1.64
     bought
    1.55
     buying
    1.52
     purchasing
    1.52
    purchased
    1.46
     purchases
    1.45
     Purchased
    1.39
     buys
    1.37
    purchase
    1.37
    Activations Density 0.368%

    No Known Activations