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. 16-GEMMASCOPE-RES-16K
    6. 6334
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML and CSS structure in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML DOCTYPE declarations

    np_acts-logits-general · gemini-2.0-flash

    DOCTYPE html and stylesheet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
     Dessa
    -0.52
     Mancha
    -0.52
     snippetHide
    -0.52
     nahilalakip
    -0.51
    بوابة
    -0.50
     autoradio
    -0.49
     gynhyrchwyd
    -0.49
     MonoBehaviour
    -0.49
     InputDecoration
    -0.47
    POSITIVE LOGITS
    jspx
    1.74
    unfinished
    0.99
    +#+#
    0.87
    {@
    0.79
    ChildScrollView
    0.78
    ftagPool
    0.72
    abstractmethod
    0.68
    ::~
    0.61
    ISupport
    0.61
     cref
    0.57
    Activations Density 0.007%

    No Known Activations