© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7329
    Prev
    Next
    INDEX
    Explanations

    references to divine or mythical entities and their influence on the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    országban
    -0.54
     démocr
    -0.53
    newswire
    -0.52
     smtplib
    -0.52
     sociala
    -0.51
    resave
    -0.51
    sizeCache
    -0.51
    oosevelt
    -0.50
    tagHelperRunner
    -0.50
     Commiss
    -0.50
    POSITIVE LOGITS
     cultivation
    0.90
     cultivators
    0.86
     cultivator
    0.84
     Sect
    0.78
    Culti
    0.78
     refining
    0.76
     sect
    0.75
    Sect
    0.74
     disciple
    0.73
     disciples
    0.71
    Activations Density 0.093%

    No Known Activations