Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 3722
    Prev
    Next
    INDEX
    Explanations

    terms related to knee injuries and anatomical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пред
    -0.50
    はじめに
    -0.45
     selera
    -0.45
     Photocase
    -0.43
     bakgrund
    -0.43
    IonicModule
    -0.42
    }))
    
    -0.42
    warzys
    -0.42
     acaso
    -0.41
    odles
    -0.41
    POSITIVE LOGITS
     Paix
    0.66
     Hem
    0.65
     Bourgoin
    0.63
     kneel
    0.62
     remand
    0.59
    jspx
    0.59
     bờ
    0.58
     hemat
    0.58
     knee
    0.57
     kneeling
    0.57
    Activations Density 3.409%

    No Known Activations