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. 11661
    Prev
    Next
    INDEX
    Explanations

    terms related to funding and financial contributions for projects, particularly in the context of education and community improvements

    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
     GenerationType
    -0.76
     الحره
    -0.73
    TintMode
    -0.69
    Datuak
    -0.65
    \{\\
    -0.65
     Efq
    -0.64
    protoimpl
    -0.62
    ьаж
    -0.62
     configureStore
    -0.61
    
    -0.60
    POSITIVE LOGITS
    InputTagHelper
    0.61
    ReusableCell
    0.59
    migrationBuilder
    0.59
     Westen
    0.56
    Geplaatst
    0.55
    الإنجليزية
    0.52
     equipment
    0.52
    JTable
    0.51
    odils
    0.49
    "/>
    
    0.47
    Activations Density 0.299%

    No Known Activations