Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 33
    Prev
    Next
    INDEX
    Explanations

    characters and their roles in a story or narrative context

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.63
    Gambas
    -0.62
     tindak
    -0.47
     tartalomajánló
    -0.44
    新年
    -0.44
     вікісторінку
    -0.43
    readystatechange
    -0.43
     intractable
    -0.43
    Биография
    -0.42
    оргаш
    -0.41
    POSITIVE LOGITS
    queryInterface
    0.55
    Personendaten
    0.51
    plish
    0.42
    ArgumentParser
    0.41
    didSet
    0.39
     personnage
    0.39
     character
    0.39
     Character
    0.38
     roles
    0.38
     role
    0.37
    Activations Density 0.100%

    No Known Activations