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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 6838
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure in documents, likely related to sections or commands in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     quelconque
    -0.78
    InSection
    -0.72
     quelcon
    -0.72
    ंदीखरीदारी
    -0.71
    ThroughAttribute
    -0.71
    IntoConstraints
    -0.71
     exclusions
    -0.66
    ineno
    -0.64
    ِّف
    -0.62
    oredCriteria
    -0.61
    POSITIVE LOGITS
    WaitGroup
    0.53
     multi
    0.52
    rein
    0.49
    saga
    0.48
     and
    0.45
     designed
    0.44
     focused
    0.44
     resource
    0.43
     spin
    0.43
    homonymie
    0.43
    Activations Density 0.288%

    No Known Activations