Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 5281
    Prev
    Next
    INDEX
    Explanations

    element attributes in XML or layout files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.10
    IsContent
    -0.92
    contentLoaded
    -0.92
     مشين
    -0.90
    FunctionFlags
    -0.90
    ViewFeatures
    -0.87
     betweenstory
    -0.87
    OGND
    -0.87
     فريبيس
    -0.85
    MENAFN
    -0.85
    POSITIVE LOGITS
    abbix
    0.52
     történ
    0.50
     recue
    0.49
     inaczej
    0.49
    omitempty
    0.46
     précis
    0.46
    bares
    0.46
    recursive
    0.46
     open
    0.45
    guna
    0.44
    Activations Density 0.012%

    No Known Activations