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. 10037
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and elements indicative of code structure

    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
    mana
    -0.50
     parlando
    -0.45
     acuer
    -0.45
     problemet
    -0.43
     året
    -0.41
    xaml
    -0.40
     ovvero
    -0.40
     cioè
    -0.39
     harmonize
    -0.39
     cilind
    -0.39
    POSITIVE LOGITS
     paramInt
    1.23
     paramString
    1.18
    
    1.10
     iParam
    1.10
    RegressionTest
    0.94
     localObject
    0.94
    __*/
    0.92
    #+#
    0.91
    NewLabel
    0.88
    ⓧ
    0.85
    Activations Density 0.282%

    No Known Activations