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. 5-GEMMASCOPE-RES-16K
    6. 11326
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "will" or "willpower."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.67
     gainera
    -0.58
     فار
    -0.58
    tonsoft
    -0.57
    SpringBootTest
    -0.54
    "]);
    
    -0.53
     Ause
    -0.53
     批
    -0.52
    ัฒ
    -0.51
    findpost
    -0.50
    POSITIVE LOGITS
     wills
    1.17
     willed
    1.09
     volontà
    0.92
     voluntad
    0.89
     desire
    0.83
     desires
    0.82
     Willen
    0.82
     volonté
    0.82
     voli
    0.81
     willpower
    0.80
    Activations Density 0.204%

    No Known Activations