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. 22-GEMMASCOPE-RES-16K
    6. 14113
    Prev
    Next
    INDEX
    Explanations

    concepts and mentions related to intelligence and smart technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.07
    évaluateur
    -0.84
     المعيارى
    -0.78
     resourceCulture
    -0.77
    WriteTagHelper
    -0.75
     CreateTagHelper
    -0.74
    ThemeOverlay
    -0.74
    yntaxException
    -0.71
     Walkover
    -0.69
    LabelTagHelper
    -0.69
    POSITIVE LOGITS
     smart
    0.64
     Smart
    0.64
     Alec
    0.58
    alec
    0.58
     SMART
    0.57
     money
    0.57
    Smart
    0.55
    smar
    0.55
     Smar
    0.55
    est
    0.53
    Activations Density 0.083%

    No Known Activations