© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 59213
    Prev
    Next
    INDEX
    Explanations

    variations of the word "bec," likely indicating specific coding or technical terms

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

    bec followed by co, ase, or quel

    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
     Eichen
    -0.50
     Eu
    -0.47
    ntown
    -0.46
     Woodruff
    -0.45
     Rauch
    -0.45
     Laub
    -0.44
    Eisen
    -0.43
    Stereo
    -0.42
     Eisen
    -0.42
     Sulphur
    -0.42
    POSITIVE LOGITS
    Bec
    2.33
     Bec
    2.33
    bec
    2.31
     bec
    2.00
    BEC
    1.96
     BEC
    1.88
    bek
    1.51
    beck
    1.47
     Bek
    1.34
     Becca
    1.34
    Activations Density 0.005%

    No Known Activations