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. 12280
    Prev
    Next
    INDEX
    Explanations

    intensifiers or adverbs that emphasize the degree or strength of various attributes or actions

    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
     мәкал
    -0.62
    windowFixed
    -0.60
    ArgsConstructor
    -0.60
     Paglinawan
    -0.56
    specifier
    -0.54
     basta
    -0.52
     Yani
    -0.52
     ComVisible
    -0.52
    เดิม
    -0.52
     durar
    -0.51
    POSITIVE LOGITS
     heavily
    1.06
     strongly
    1.03
     deeply
    0.94
     intensely
    0.94
    strongly
    0.90
     greatly
    0.89
     fortement
    0.87
     highly
    0.83
     Strongly
    0.78
     fuertemente
    0.78
    Activations Density 0.409%

    No Known Activations