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. 0-GEMMASCOPE-RES-16K
    6. 7827
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lined" and related syntactic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.86
    SEGUIR
    -0.86
     שוליים
    -0.86
     surla
    -0.85
    ंदीखरीदारी
    -0.84
    sidemargin
    -0.81
     HasFactory
    -0.80
    Приятного
    -0.79
    Билгалдахарш
    -0.78
    曖昧さ回避
    -0.77
    POSITIVE LOGITS
     lined
    0.72
    za
    0.60
    ___
    0.57
    ประ
    0.53
     mixing
    0.51
    で
    0.49
     ประ
    0.48
     really
    0.47
     б
    0.47
     na
    0.46
    Activations Density 0.114%

    No Known Activations