© 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. 7-GEMMASCOPE-RES-16K
    11. 8354
    Prev
    Next
    INDEX
    Explanations

    specific lexical items or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aéri
    -0.52
     Aner
    -0.52
    ktır
    -0.51
     casamento
    -0.47
     ligiloj
    -0.47
     parallèle
    -0.46
     kaybet
    -0.45
     religieuses
    -0.45
     Insee
    -0.44
    uyor
    -0.44
    POSITIVE LOGITS
    Дереккөздер
    0.75
    नलिखित
    0.74
    WriteBarrier
    0.73
    
    0.72
    awtextra
    0.71
     IActionResult
    0.71
     ModelExpression
    0.71
    LookAnd
    0.70
    </tfoot>
    0.65
    期刊论文
    0.64
    Activations Density 0.032%

    No Known Activations