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. 20-GEMMASCOPE-RES-16K
    6. 7605
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions indicating difficulty or challenges faced in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.88
    brigens
    -0.72
     متعلقه
    -0.71
    AndEndTag
    -0.68
    ValueStyle
    -0.67
    windowFixed
    -0.67
     समीक्षक
    -0.64
    DockStyle
    -0.63
    ItemBackground
    -0.62
    CodeAttribute
    -0.62
    POSITIVE LOGITS
     challenging
    1.32
     daunting
    1.17
     difficult
    1.12
     Challenging
    1.10
     arduous
    1.06
     exhausting
    1.04
     challenge
    1.02
     tedious
    1.00
     stressful
    0.97
    chall
    0.96
    Activations Density 0.312%

    No Known Activations