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. 20-GEMMASCOPE-RES-131K
    6. 73534
    Prev
    Next
    INDEX
    Explanations

    frequently used modal verbs and pronouns in the context of expressing uncertainty or potentiality

    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
    :✨
    -0.35
     faute
    -0.35
    Xna
    -0.30
     Poste
    -0.28
     sout
    -0.28
     Bonds
    -0.27
     annan
    -0.27
    #+#
    -0.26
    atalos
    -0.25
     prodi
    -0.25
    POSITIVE LOGITS
    Personendaten
    0.75
     nonUne
    0.58
    ImageContext
    0.55
     AssemblyCulture
    0.52
    keyColumn
    0.51
     للمعارف
    0.50
     rozwią
    0.50
    PRNewswire
    0.50
    IContainer
    0.49
    TypedDataSet
    0.49
    Activations Density 0.049%

    No Known Activations