© 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. 21-GEMMASCOPE-RES-16K
    11. 1076
    Prev
    Next
    INDEX
    Explanations

    phrases containing contractions and apostrophes, often associated with informal speech or writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ...
    -0.76
    ...
    -0.71
     …
    -0.70
    …
    -0.68
     ("
    -0.65
     (“
    -0.62
     Einfluß
    -0.59
    .../
    -0.58
     […]
    -0.56
    ･･･
    -0.56
    POSITIVE LOGITS
     Um
    0.79
    Um
    0.79
    Personendaten
    0.75
     Uh
    0.72
    Uh
    0.66
     resourceCulture
    0.64
    IUrlHelper
    0.63
    存于互联网档案馆
    0.62
    interopRequire
    0.61
     um
    0.61
    Activations Density 0.044%

    No Known Activations