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. 1579
    Prev
    Next
    INDEX
    Explanations

    references to portals or related navigational concepts

    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
    ValueStyle
    -0.78
     MONO
    -0.70
     monoc
    -0.68
     Soldiers
    -0.67
     Ponce
    -0.66
     Mono
    -0.66
     Sando
    -0.66
     mono
    -0.65
    es
    -0.65
     Sato
    -0.64
    POSITIVE LOGITS
    بوابة
    0.74
     Holman
    0.69
     المعيارى
    0.67
    enumii
    0.64
     portail
    0.63
    prnewswire
    0.62
     Wikimédia
    0.61
    معلومات
    0.60
    #+#
    0.60
    tonsoft
    0.58
    Activations Density 0.141%

    No Known Activations