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. 12250
    Prev
    Next
    INDEX
    Explanations

    actions related to completing and submitting forms and applications

    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
    GoogleApiClient
    -0.50
    UnitTesting
    -0.50
     @}
    -0.48
     CGSize
    -0.47
     متعلقه
    -0.47
    withIdentifier
    -0.46
    .*")]
    -0.46
    Portail
    -0.45
     насељу
    -0.45
    下一篇
    -0.44
    POSITIVE LOGITS
     forms
    0.95
     Forms
    0.91
    Forms
    0.90
     FORMS
    0.87
     paperwork
    0.84
     Form
    0.84
    forms
    0.83
     form
    0.80
     FORM
    0.77
     questionnaires
    0.77
    Activations Density 0.344%

    No Known Activations