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

    Neuronpedia

    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. 6-GEMMASCOPE-RES-16K
    11. 6932
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific attributes and details that describe objects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Whilst
    -1.47
     Whilst
    -1.41
     realised
    -1.23
    initialise
    -1.19
     tyres
    -1.18
     whilst
    -1.18
     specialises
    -1.17
     realising
    -1.17
     enquiries
    -1.16
     realise
    -1.16
    POSITIVE LOGITS
     confiable
    1.16
     parlor
    1.14
     favors
    1.10
     flavorful
    1.09
    ônicos
    1.06
     favorably
    1.04
    Neighbors
    1.03
     flavors
    1.03
     neighbors
    1.03
     Neighbors
    1.02
    Activations Density 7.048%

    No Known Activations