© 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. 5-GEMMASCOPE-RES-16K
    11. 15639
    Prev
    Next
    INDEX
    Explanations

    words related to assurance and guarantees regarding quality or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    talk
    -0.69
    wę
    -0.67
     talk
    -0.65
    Brat
    -0.62
     fritas
    -0.61
    Notae
    -0.61
     Pollard
    -0.61
    ächlich
    -0.60
     fVar
    -0.60
    tubes
    -0.60
    POSITIVE LOGITS
     ensured
    1.72
     ensures
    1.70
     Ensure
    1.70
     ensure
    1.68
    Ensure
    1.65
     ensuring
    1.63
     Ensuring
    1.46
    ensure
    1.42
     Ens
    1.26
     insure
    1.25
    Activations Density 0.054%

    No Known Activations