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. 4396
    Prev
    Next
    INDEX
    Explanations

    HTML or XML elements related to user interface components

    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
    CodeAttribute
    -0.67
    badlogic
    -0.59
    Österreich
    -0.55
    HttpHeaders
    -0.55
     DevExpress
    -0.54
    DateFormat
    -0.54
    XmlEnum
    -0.54
    انجليز
    -0.53
    др
    -0.48
    XtraReports
    -0.47
    POSITIVE LOGITS
    PerformLayout
    1.05
    dirname
    0.94
    TagHelper
    0.88
    BeginContext
    0.84
    ReactDOM
    0.81
     ویکی‌پدیای
    0.78
    ViewGroup
    0.75
    ngOnInit
    0.75
     dirname
    0.75
    rungsseite
    0.75
    Activations Density 0.008%

    No Known Activations