Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 10903
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "work" and its variations, indicating functionality and effectiveness

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LabelTagHelper
    -0.70
    olyte
    -0.58
    ilisation
    -0.55
    Agora
    -0.55
     للمعارف
    -0.54
    orianCalendar
    -0.53
    ιώ
    -0.53
     avs
    -0.52
    »։
    -0.51
     marke
    -0.50
    POSITIVE LOGITS
     works
    0.88
     funguje
    0.84
     funktioniert
    0.84
     Works
    0.79
     fungerar
    0.79
     WORKS
    0.78
     miracles
    0.77
     worked
    0.77
    Works
    0.77
    works
    0.76
    Activations Density 0.167%

    No Known Activations