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. 10565
    Prev
    Next
    INDEX
    Explanations

    references to the Internet and its applications

    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
     MonoBehaviour
    -0.67
    findpost
    -0.64
     protoimpl
    -0.61
    ConstraintMaker
    -0.60
    évaluateur
    -0.59
    UIControlState
    -0.59
     Nachhaltigkeit
    -0.58
     zau
    -0.58
    cessite
    -0.58
    stretchr
    -0.56
    POSITIVE LOGITS
     Internet
    2.50
    Internet
    2.30
     internet
    2.28
     INTERNET
    2.15
    internet
    2.10
    INTERNET
    1.88
     Интернет
    1.33
    互联网
    1.32
     интернет
    1.28
     الإنترنت
    1.28
    Activations Density 0.039%

    No Known Activations