© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6547
    Prev
    Next
    INDEX
    Explanations

    words with the suffix 'ized' or 'isation'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.55
     enqu
    -0.50
     Laur
    -0.47
    Micha
    -0.47
    әр
    -0.46
    сторія
    -0.43
    Token
    -0.42
     nech
    -0.41
    kea
    -0.41
    setattr
    -0.40
    POSITIVE LOGITS
    ized
    3.06
    ize
    2.71
    izing
    2.49
    IZED
    2.46
    ization
    2.45
    izes
    2.29
    ised
    2.16
    IZE
    2.11
    izations
    2.05
    IZATION
    2.00
    Activations Density 0.087%

    No Known Activations