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. 14639
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical development and biotechnology

    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
    URLException
    -0.75
     препратки
    -0.73
    picasso
    -0.67
     semula
    -0.65
    PackageManager
    -0.63
    ritation
    -0.63
    Panamoan
    -0.61
    andExpect
    -0.61
     invokevirtual
    -0.60
     possesso
    -0.60
    POSITIVE LOGITS
    PhysRevD
    1.25
     DPR
    1.03
     DCA
    1.00
     DAP
    0.99
     DCP
    0.98
     DSA
    0.98
     DMR
    0.98
     DSS
    0.98
     DTS
    0.97
     DPM
    0.96
    Activations Density 3.726%

    No Known Activations