Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45448
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.94
    UnusedPrivate
    -0.90
    WebVitals
    -0.83
    HomeAsUpEnabled
    -0.83
     تضيفلها
    -0.83
     pinulongan
    -0.83
    delwed
    -0.82
     ujednoznacz
    -0.81
    IndentedString
    -0.80
     invokingState
    -0.80
    POSITIVE LOGITS
     algorithms
    0.30
     and
    0.30
     obicei
    0.28
     pains
    0.27
     Sure
    0.27
     
    0.27
     Preise
    0.27
     engines
    0.27
     tables
    0.26
    grafías
    0.25
    Activations Density 0.001%

    No Known Activations