© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1588
    Prev
    Next
    INDEX
    Explanations

    the word "who" and variations of it, indicating a focus on relative clauses or descriptions related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réguli
    -0.79
    IsPostBack
    -0.78
    pushFollow
    -0.76
     AssemblyCulture
    -0.76
    __':
    -0.75
     AssemblyCompany
    -0.75
     démocr
    -0.73
     pouvoirs
    -0.73
    
    -0.73
    IsContent
    -0.73
    POSITIVE LOGITS
     którzy
    0.78
     kteří
    0.74
     themselves
    0.74
     are
    0.73
     които
    0.63
    wsze
    0.62
    zeczy
    0.60
     אלה
    0.60
     their
    0.60
     kinds
    0.59
    Activations Density 0.183%

    No Known Activations