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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76280
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to quantities, particularly related to repetition or enumeration

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

    counting and sequences

    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
     sını
    -0.55
     Barros
    -0.53
     Ochoa
    -0.50
     Islas
    -0.49
     Ansatz
    -0.49
     Westen
    -0.48
     Cortés
    -0.48
     Cardoso
    -0.48
     Mendez
    -0.47
    <h3>
    -0.47
    POSITIVE LOGITS
    的一
    0.99
    有一
    0.96
    还有一
    0.86
    了一
    0.85
    出一
    0.79
    是一
    0.79
    着一
    0.77
    出了一
    0.71
    只有一
    0.69
    上一
    0.67
    Activations Density 0.002%

    No Known Activations