© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39804
    Prev
    Next
    INDEX
    Explanations

    all variations of the word 'effort' across different contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.81
     يتيمه
    -0.77
    UVWXYZ
    -0.74
     PSM
    -0.74
    ,$_
    -0.73
    yntaxException
    -0.72
    orance
    -0.71
    IBarButtonItem
    -0.69
     HttpNotFound
    -0.68
     DeL
    -0.66
    POSITIVE LOGITS
     effort
    1.88
     efforts
    1.80
     Effort
    1.73
     Efforts
    1.70
    Effort
    1.52
     EFF
    1.45
    effort
    1.41
    efforts
    1.35
     attempts
    1.19
     esforço
    1.12
    Activations Density 0.013%

    No Known Activations