© 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. 24-GEMMASCOPE-RES-16K
    11. 13878
    Prev
    Next
    INDEX
    Explanations

    instances of relational or comparative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding a/an in a sentence

    np_acts-logits-general · gemini-2.0-flash

    a phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sebuah
    -0.77
     seorang
    -0.76
    A
    -0.76
    an
    -0.70
    another
    -0.69
    一位
    -0.68
     eines
    -0.66
     A
    -0.66
     einem
    -0.63
     einen
    -0.63
    POSITIVE LOGITS
    aarrggbb
    0.86
     وتسجيلات
    0.82
    ValueStyle
    0.82
     Monfieur
    0.78
    ftagPool
    0.78
     Offisielt
    0.75
     defaultstate
    0.75
     myſelf
    0.75
    )))));
    0.73
     againſt
    0.72
    Activations Density 0.534%

    No Known Activations