© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 20096
    Prev
    Next
    INDEX
    Explanations

    phrases related to frequency and occurrence

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

    often times

    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
     ARRANG
    -0.39
    بوابة
    -0.38
    organ
    -0.38
    nande
    -0.38
     Briefly
    -0.37
    ↕
    -0.37
     suman
    -0.37
     proced
    -0.36
    prev
    -0.35
    nir
    -0.35
    POSITIVE LOGITS
     oftentimes
    1.12
    Often
    0.97
     Often
    0.94
     often
    0.89
     spesso
    0.88
    Oft
    0.88
     Oft
    0.85
    often
    0.83
     souvent
    0.81
     często
    0.78
    Activations Density 0.023%

    No Known Activations