© 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. 10427
    Prev
    Next
    INDEX
    Explanations

    concepts related to design and identity in various contexts

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

    following "in" or indicating preference

    np_acts-logits-general · gemini-2.0-flash

    favoring or replacing

    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
    RectangleBorder
    -0.66
    RegistryLite
    -0.66
    SBATCH
    -0.66
     مشين
    -0.65
     NSError
    -0.64
     fermés
    -0.64
    expandindo
    -0.64
     alimentaire
    -0.60
    parsedMessage
    -0.60
     pleins
    -0.59
    POSITIVE LOGITS
     favor
    1.46
     favour
    1.41
     replaced
    1.32
     preferring
    1.23
    favor
    1.18
     favoring
    1.09
    replaced
    1.09
     favore
    1.00
    fav
    1.00
     Replaced
    0.99
    Activations Density 0.327%

    No Known Activations