Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12891
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alloc" and components related to Vue framework in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.82
    Sucesor
    -0.77
    InputBorder
    -0.73
    unknownFields
    -0.72
    EndProject
    -0.72
    TemporalType
    -0.70
     تضيفلها
    -0.68
    bootstrapcdn
    -0.64
    verifyException
    -0.64
    Література
    -0.64
    POSITIVE LOGITS
    vue
    3.49
     Vue
    2.90
    Vue
    2.84
     vue
    2.26
     "@/
    1.28
    vues
    1.21
     '@/
    1.17
     vues
    1.17
    vu
    0.82
     Vu
    0.77
    Activations Density 0.052%

    No Known Activations