© 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. 6820
    Prev
    Next
    INDEX
    Explanations

    instances of the word "through" in different contexts, indicating a focus on exploration or passage

    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
     pulumi
    -0.57
    ttet
    -0.55
     Ganz
    -0.53
     CNRS
    -0.52
     Lyon
    -0.52
     ajutor
    -0.52
    
    -0.52
    GEBURTSDATUM
    -0.52
    artan
    -0.51
    tivity
    -0.51
    POSITIVE LOGITS
     through
    1.13
    through
    1.08
    Through
    1.01
    THROUGH
    0.96
     Through
    0.95
     walkthrough
    0.93
     Walkthrough
    0.89
     gjennom
    0.88
     THROUGH
    0.88
     attravers
    0.86
    Activations Density 0.086%

    No Known Activations