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. 21-GEMMASCOPE-RES-16K
    6. 7039
    Prev
    Next
    INDEX
    Explanations

    assignment operations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satunya
    -0.50
    estacks
    -0.50
    Altre
    -0.47
    CodedInputStream
    -0.47
    Pautan
    -0.44
     başına
    -0.43
     kanssa
    -0.43
    Rujukan
    -0.42
    AndGet
    -0.41
    DataArray
    -0.41
    POSITIVE LOGITS
     surla
    0.84
     विश्वसनीयता
    0.76
    ")));
    
    0.74
     resourceCulture
    0.73
     CreateTagHelper
    0.73
    PerformLayout
    0.70
    ]));
    
    0.68
    ⓧ
    0.66
     дописавши
    0.65
    IsContent
    0.64
    Activations Density 0.006%

    No Known Activations