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. 7246
    Prev
    Next
    INDEX
    Explanations

    expressions of social disruption and culinary experiences

    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
     
    -0.52
     Com
    -0.50
    <eos>
    -0.49
    alnız
    -0.47
    Survivors
    -0.46
    падает
    -0.46
     com
    -0.45
    出して
    -0.45
     ?
    -0.45
    fek
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.99
    numerusform
    0.93
    QMetaType
    0.88
    AnimationsModule
    0.79
    Vidite
    0.77
     Normdatei
    0.76
    ngdoc
    0.76
    sidemargin
    0.75
     disambiguazione
    0.75
     للمعارف
    0.74
    Activations Density 0.067%

    No Known Activations