© 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. 9266
    Prev
    Next
    INDEX
    Explanations

    terms associated with magical abilities and spells

    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
    Geplaatst
    -0.58
    xhtml
    -0.55
    AsUp
    -0.54
    XmlSchema
    -0.51
    GEBURTS
    -0.48
    intahan
    -0.47
    olverine
    -0.46
    exitRule
    -0.46
    omitempty
    -0.46
    zzlies
    -0.45
    POSITIVE LOGITS
     magic
    1.85
     Magic
    1.62
    magic
    1.57
     spells
    1.57
    Magic
    1.54
     magia
    1.54
     magical
    1.53
     spell
    1.53
     MAGIC
    1.49
     magicians
    1.47
    Activations Density 0.525%

    No Known Activations