© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    key phrases and elements related to decision making and criteria assessment

    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
     CreateTagHelper
    -0.69
    ="?
    -0.60
    )))));
    -0.53
    ))));
    -0.53
    ArgsConstructor
    -0.51
     Bourgoin
    -0.51
     XCTest
    -0.50
    autoreleasepool
    -0.50
    ettes
    -0.49
    лтемелер
    -0.48
    POSITIVE LOGITS
    出版年
    0.65
    crollView
    0.54
     onAnimation
    0.50
     ſche
    0.50
    ocular
    0.48
    keyColumn
    0.47
    視
    0.46
     favorably
    0.46
     punitive
    0.46
     you
    0.46
    Activations Density 0.456%

    No Known Activations