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. 4236
    Prev
    Next
    INDEX
    Explanations

    terms related to wounds and injuries

    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
     bl
    -0.51
    ʊ
    -0.50
    ут
    -0.49
    gogo
    -0.48
    addElement
    -0.48
    曖昧さ回避
    -0.47
    /*
    -0.47
    addAttribute
    -0.47
    μαι
    -0.46
    ه‌اند
    -0.46
    POSITIVE LOGITS
     cracks
    1.08
     Cracks
    0.96
     holes
    0.85
     defects
    0.84
     crack
    0.83
     fissure
    0.83
     fissures
    0.82
     hole
    0.82
    crack
    0.81
     fractures
    0.81
    Activations Density 0.382%

    No Known Activations