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. 15-GEMMASCOPE-RES-16K
    6. 2470
    Prev
    Next
    INDEX
    Explanations

    sequences involving numerical or categorical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.33
     ویکی‌پدیای
    -1.18
     CreateTagHelper
    -1.13
    aarrggbb
    -1.11
     betweenstory
    -1.11
     дописавши
    -1.08
    AndEndTag
    -1.05
     مرئيه
    -1.04
    webElementXpaths
    -1.03
     GetEnumerator
    -1.03
    POSITIVE LOGITS
     
    0.61
     La
    0.53
    <sup>
    0.52
    ,
    0.51
     of
    0.49
    :
    0.49
    1
    0.48
     Th
    0.47
     The
    0.47
     car
    0.46
    Activations Density 0.742%

    No Known Activations