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. 5254
    Prev
    Next
    INDEX
    Explanations

    references to research funding sources

    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
     الرياضيه
    -0.87
    حياته
    -0.81
     Савезне
    -0.71
    Portale
    -0.65
    expandindo
    -0.63
     CreateTagHelper
    -0.63
    WriteBarrier
    -0.63
     تضيفلها
    -0.61
     estekak
    -0.61
    SharedDtor
    -0.60
    POSITIVE LOGITS
     grants
    0.58
     contado
    0.57
     grant
    0.55
    migrationBuilder
    0.55
     Grants
    0.54
     funded
    0.53
     financeiro
    0.49
     funding
    0.48
    Grants
    0.46
     financi
    0.45
    Activations Density 0.393%

    No Known Activations