© 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. 8-GEMMASCOPE-RES-16K
    6. 3012
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or events from the Harry Potter series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -1.16
    ConstraintMaker
    -0.87
    }],
    
    -0.85
     &___
    -0.84
    :✨
    -0.83
    ValueStyle
    -0.81
    TagMode
    -0.81
     CURIAM
    -0.80
    elemField
    -0.79
     BoxFit
    -0.79
    POSITIVE LOGITS
     Hogwarts
    0.82
     Rowling
    0.68
    umbledore
    0.60
     Dumbledore
    0.59
     Hermione
    0.59
     Weasley
    0.58
    Hermione
    0.56
     Malfoy
    0.55
     Potter
    0.54
    ffindor
    0.54
    Activations Density 0.157%

    No Known Activations