© 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. 4033
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and recommendations related to decision-making

    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
    InstrumentedTest
    -0.71
    Portály
    -0.66
     @"/
    -0.63
    eterangan
    -0.55
     ActionListener
    -0.54
     useAppContext
    -0.53
    "](
    -0.52
    
    -0.51
    BufferException
    -0.51
    thrown
    -0.50
    POSITIVE LOGITS
     lieber
    0.70
     Betracht
    0.70
     sooner
    0.69
     inkább
    0.63
     rather
    0.59
     instead
    0.58
     plutôt
    0.56
     zumal
    0.56
     Administrativna
    0.56
     whichever
    0.55
    Activations Density 0.306%

    No Known Activations