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. 11-GEMMASCOPE-RES-16K
    6. 6226
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical analysis and data processing within scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.91
    ագրություններ
    -0.88
     CreateTagHelper
    -0.76
    GOTREF
    -0.64
    Legături
    -0.64
     Chwiliwch
    -0.62
    出版年
    -0.60
    
    -0.60
     preſent
    -0.59
     CYTHON
    -0.59
    POSITIVE LOGITS
    annica
    0.60
    djangoproject
    0.51
     juridiques
    0.50
    Демографія
    0.46
     expédi
    0.46
     opérateur
    0.42
     Viator
    0.42
    igslist
    0.41
    いう
    0.41
    rovnik
    0.41
    Activations Density 0.645%

    No Known Activations