© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1233
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations and dependencies in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.72
    таратура
    -0.69
    ंदीखरीदारी
    -0.65
    Handlung
    -0.65
    ੝
    -0.65
     pinulongan
    -0.63
    SourceChecksum
    -0.63
     Lokales
    -0.60
     وتسجيلات
    -0.59
    ToAction
    -0.58
    POSITIVE LOGITS
    specific
    0.33
    isalpha
    0.31
     balance
    0.28
    resolve
    0.27
     aż
    0.27
     yhte
    0.27
     équilibr
    0.27
     compensated
    0.26
     tissue
    0.26
    balance
    0.26
    Activations Density 1.114%

    No Known Activations