© 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. 11-GEMMASCOPE-RES-16K
    11. 12978
    Prev
    Next
    INDEX
    Explanations

    instances of the word "correct" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.95
    Hauptartikel
    -0.90
     بيها
    -0.86
    ManagedBean
    -0.82
     AppBundle
    -0.82
     SizedBox
    -0.81
    ]-->
    -0.81
    userManager
    -0.81
    waitKey
    -0.80
     asunder
    -0.80
    POSITIVE LOGITS
     CORRECT
    1.43
     Correct
    1.42
    Correct
    1.30
     correct
    1.29
    correct
    1.17
     correctness
    1.12
     corect
    1.11
     corrects
    1.08
    CORRECT
    1.03
     correc
    0.99
    Activations Density 0.062%

    No Known Activations