© 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. 4-GEMMASCOPE-RES-16K
    11. 1836
    Prev
    Next
    INDEX
    Explanations

    the word "apart" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.77
    cy
    -0.70
    dotenv
    -0.70
    e
    -0.70
    a
    -0.68
    N
    -0.61
     T
    -0.60
     +
    -0.60
    >+</
    -0.60
    n
    -0.58
    POSITIVE LOGITS
     apart
    2.76
    apart
    2.52
     Apart
    2.35
    Apart
    2.15
     APART
    1.90
     aside
    1.89
    aside
    1.69
     Aside
    1.66
    Aside
    1.63
     appart
    1.48
    Activations Density 0.055%

    No Known Activations