© 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. 10-GEMMASCOPE-RES-16K
    11. 8439
    Prev
    Next
    INDEX
    Explanations

    phrases related to the highest and lowest values, especially in a mathematical or comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    -0.96
    er
    -0.92
    p
    -0.87
    o
    -0.86
    u
    -0.84
    a
    -0.83
    k
    -0.83
    r
    -0.82
    q
    -0.77
     Man
    -0.75
    POSITIVE LOGITS
     beſt
    1.34
     greateſt
    1.29
    ]")]
    1.28
     myſelf
    1.27
     leaſt
    1.25
     firſt
    1.23
     ་་
    1.21
    apest
    1.19
     Majefty
    1.16
    </tfoot>
    1.15
    Activations Density 0.052%

    No Known Activations