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. 11993
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of streets and locations

    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
     كومونز
    -0.64
     通販
    -0.59
    ).</
    -0.59
    '],
    
    -0.57
    ).
    
    -0.55
    enumii
    -0.54
     GetEnumerator
    -0.54
    "],
    
    -0.53
    AccessorTable
    -0.53
    }}$\\
    -0.52
    POSITIVE LOGITS
     Paglinawan
    0.53
     etmeye
    0.51
    sidemargin
    0.50
    fromnode
    0.50
     plantel
    0.48
     aikana
    0.47
     vektör
    0.47
    DialogContent
    0.47
     ClassNotFound
    0.47
    WindowConstants
    0.46
    Activations Density 0.310%

    No Known Activations