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. 12-GEMMASCOPE-RES-16K
    6. 12534
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PG
    -0.52
    IBOutlet
    -0.50
    
    -0.50
    LookAnd
    -0.47
    ք
    -0.45
    ọa
    -0.42
     razor
    -0.42
    djangoproject
    -0.42
    doj
    -0.41
    icating
    -0.41
    POSITIVE LOGITS
    中略
    0.77
    PerformLayout
    0.75
     &___
    0.71
    [:]
    0.69
    [,]
    0.68
    WritableDatabase
    0.68
     förr
    0.64
     (…)
    0.63
     magique
    0.62
    [...,
    0.61
    Activations Density 0.133%

    No Known Activations