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. 1867
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurements and computations

    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
     referenties
    -0.78
     Roskov
    -0.78
    DebuggerStep
    -0.77
     AssemblyVersion
    -0.68
    RegistryLite
    -0.67
     betweenstory
    -0.66
    <bos>
    -0.64
    carbons
    -0.64
     متعلقه
    -0.62
    ///**
    -0.62
    POSITIVE LOGITS
    ValueStyle
    0.54
     genoux
    0.49
     isNameExpr
    0.48
     Мексичка
    0.45
     demandent
    0.45
     verbonden
    0.44
     demasi
    0.44
     capaces
    0.41
    brać
    0.41
     offrent
    0.41
    Activations Density 1.287%

    No Known Activations