© 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. 10-GEMMASCOPE-RES-16K
    6. 6520
    Prev
    Next
    INDEX
    Explanations

    keywords related to 'Harry Potter' and characters or elements from the series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.81
    esgue
    -0.78
    +#+
    -0.74
     BoxFit
    -0.72
    }],
    
    -0.65
     ExecuteAsync
    -0.62
    godic
    -0.62
    fjspx
    -0.61
     发表于
    -0.61
     AssemblyTitle
    -0.61
    POSITIVE LOGITS
     Hogwarts
    0.83
     Hermione
    0.55
     Jedi
    0.52
     PyLong
    0.52
     Dumbledore
    0.50
    moine
    0.49
     Firenze
    0.49
    ffindor
    0.49
     Malfoy
    0.48
    Ciri
    0.48
    Activations Density 0.104%

    No Known Activations