© 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. 644
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory matters

    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
     you
    -0.50
     aplica
    -0.48
    <em>
    -0.48
    材
    -0.47
     applications
    -0.45
     cer
    -0.44
     mã
    -0.43
     application
    -0.42
    ст
    -0.42
    ichter
    -0.42
    POSITIVE LOGITS
    RegistryLite
    1.01
     Roskov
    0.93
     */;
    0.82
    oredCriteria
    0.82
     tfsi
    0.81
    PreferredItem
    0.81
    NUMX
    0.81
    InitVars
    0.81
    StructEnd
    0.80
    setupUi
    0.79
    Activations Density 0.177%

    No Known Activations