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. 11851
    Prev
    Next
    INDEX
    Explanations

    quantum terminology and notations related to density operators and measurements

    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
     Alva
    -0.71
     Esther
    -0.68
    sok
    -0.67
    urbing
    -0.66
     Moody
    -0.66
     alimentaire
    -0.65
    vieja
    -0.65
     Xun
    -0.65
     stationnement
    -0.64
     Bouch
    -0.64
    POSITIVE LOGITS
    langle
    2.17
    rangle
    1.90
     〈
    1.14
    ⟨
    1.10
    "):
    
    0.99
    〉
    0.93
    〈
    0.92
     Walkover
    0.88
    ]),
    
    0.88
    "]);
    
    0.87
    Activations Density 0.121%

    No Known Activations