© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9633
    Prev
    Next
    INDEX
    Explanations

    references to specific football teams and players in Argentina and Turkmenistan

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

    Numbers or number ranges

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
    ”).
    -1.05
    ,”
    -0.90
    ”),
    -0.88
    ),”
    -0.88
    ).”
    -0.83
    .”
    -0.81
    ”.
    -0.80
    ”:
    -0.77
    ”,
    -0.74
     .”
    -0.74
    POSITIVE LOGITS
    </td>
    1.78
    </th>
    0.98
    <sup>
    0.90
    </i>
    0.75
    <i>
    0.75
    </b>
    0.73
    </h3>
    0.71
    <table>
    0.71
     (−
    0.69
     →
    0.65
    Activations Density 0.168%

    No Known Activations