© 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 EvalsExportsinterp-engineNEWAPI 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. 4253
    Prev
    Next
    INDEX
    Explanations

    requirements and criteria related to compliance and fulfillment

    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
    parsedMessage
    -0.62
     restTemplate
    -0.62
    addPreferredGap
    -0.59
     eft
    -0.51
    حياته
    -0.50
    IUrlHelper
    -0.49
    BLANK
    -0.49
     NgModule
    -0.49
     Serikat
    -0.49
    contentLoaded
    -0.49
    POSITIVE LOGITS
    (!__
    0.74
     adheres
    0.70
    StoreMessageInfo
    0.69
     comply
    0.67
     rules
    0.66
     complies
    0.66
     remplir
    0.66
     cumplir
    0.65
     the
    0.64
    rules
    0.64
    Activations Density 0.276%

    No Known Activations