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. 12283
    Prev
    Next
    INDEX
    Explanations

    instances of the word "preceded."

    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
    providedIn
    -0.71
    ChildScrollView
    -0.71
    multer
    -0.71
    তথ্যসূত্র
    -0.70
     BnF
    -0.68
    outine
    -0.67
     BoxFit
    -0.66
    ATIVES
    -0.66
    sizeCache
    -0.66
    romyalgia
    -0.64
    POSITIVE LOGITS
     preceded
    2.09
     precedes
    1.36
     precede
    1.31
     précé
    1.08
     predeceased
    0.90
     preceding
    0.88
    preced
    0.80
     preced
    0.80
     followed
    0.79
    ceded
    0.72
    Activations Density 0.032%

    No Known Activations