© 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. 1-GEMMASCOPE-RES-16K
    11. 13946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "actually."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.53
     åt
    -0.51
     Exacts
    -0.50
    做过
    -0.50
     Irvine
    -0.48
     pó
    -0.48
    icali
    -0.47
     говорили
    -0.46
    taller
    -0.46
     Erfüllung
    -0.46
    POSITIVE LOGITS
     actually
    0.83
    queryInterface
    0.76
    EndInit
    0.76
     merit
    0.73
    awtextra
    0.72
    >[]
    0.72
    actually
    0.70
     propOrder
    0.69
    Autoritní
    0.69
    remadura
    0.68
    Activations Density 0.097%

    No Known Activations