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. 4522
    Prev
    Next
    INDEX
    Explanations

    references to academic proceedings and publications

    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
    queryInterface
    -0.64
    ✨:
    -0.60
    ligente
    -0.53
    "}>
    -0.49
     Eup
    -0.49
     Besøkt
    -0.48
     Commercial
    -0.48
    ')):
    -0.47
    Commercial
    -0.45
     itin
    -0.44
    POSITIVE LOGITS
     Proceedings
    1.55
    Proceedings
    1.40
     Proc
    1.39
    Proc
    1.10
     PROCEEDINGS
    1.06
     proceedings
    1.03
    ceedings
    0.96
     QName
    0.81
    BeginContext
    0.80
    proc
    0.77
    Activations Density 0.064%

    No Known Activations