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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 74933
    Prev
    Next
    INDEX
    Explanations

    the structure and formatting of code or documents, particularly related to grouping or either opening or closing brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    items or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.82
    yarnpkg
    -0.69
     queſta
    -0.68
    RegressionTest
    -0.66
    ſammen
    -0.66
    ureusement
    -0.66
     cartaz
    -0.65
    WithIOException
    -0.65
    BufferException
    -0.65
    convite
    -0.63
    POSITIVE LOGITS
    itemize
    0.37
    Items
    0.32
    1
    0.29
    X
    0.29
     nakalista
    0.28
    items
    0.28
     items
    0.28
      
    0.28
    ↵
    0.27
    ML
    0.27
    Activations Density 0.003%

    No Known Activations