© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6504
    Prev
    Next
    INDEX
    Explanations

    references or citations related to academic or technical content

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

    Jupyter notebooks and dataframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.40
    liceerd
    -0.38
    ronique
    -0.37
    ParseTree
    -0.36
    AnchorTagHelper
    -0.35
     linkovi
    -0.35
     Syrie
    -0.35
    sified
    -0.35
    XmlType
    -0.35
     Enix
    -0.35
    POSITIVE LOGITS
     notebook
    0.75
    ynb
    0.73
     Jupyter
    0.69
    upyter
    0.67
    notebook
    0.65
     Notebook
    0.64
    Notebook
    0.63
     notebooks
    0.60
     dataframe
    0.55
     Notebooks
    0.54
    Activations Density 0.094%

    No Known Activations