© 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. 52020
    Prev
    Next
    INDEX
    Explanations

    references to business transactions and conditions

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

    treated as or regarded

    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
    はじめに
    -0.39
    irited
    -0.37
    Aiheesta
    -0.36
     AssemblyCompany
    -0.35
     virtud
    -0.33
     adquisición
    -0.31
     operación
    -0.31
     estábamos
    -0.30
     nepiecieš
    -0.30
     práctico
    -0.30
    POSITIVE LOGITS
     LCCN
    0.52
    хьтан
    0.51
     regard
    0.51
     SafeMath
    0.49
    regard
    0.49
    endphp
    0.49
     Targeting
    0.48
     Regard
    0.47
    URLException
    0.47
    ToProps
    0.47
    Activations Density 0.308%

    No Known Activations