© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105815
    Prev
    Next
    INDEX
    Explanations

    references to characters and events in the Harry Potter series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.50
    Personensuche
    -0.49
    pantalón
    -0.49
    Erreferentziak
    -0.44
    WebServlet
    -0.44
    chaleco
    -0.42
     صوتيه
    -0.41
     mecán
    -0.40
     Paglinawan
    -0.40
    niña
    -0.39
    POSITIVE LOGITS
    NewUrlParser
    0.49
     wizard
    0.44
    ondissement
    0.43
     wizards
    0.41
    PyExc
    0.41
     Hogwarts
    0.40
    msgSender
    0.40
     Alembic
    0.39
    InputLabel
    0.38
    London
    0.37
    Activations Density 0.027%

    No Known Activations