© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    references to specific legal cases or terms related to legal proceedings

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

    Mayo v. Henderson; MMP2; WriteTo

    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
    SBATCH
    -0.55
    LLocation
    -0.52
    NewReader
    -0.51
     Jérusalem
    -0.49
    IsContent
    -0.48
     Strukt
    -0.48
     tæ
    -0.48
    reactstrap
    -0.47
     onView
    -0.47
     akus
    -0.46
    POSITIVE LOGITS
     Mayo
    2.66
    Mayo
    2.47
     MAYO
    1.99
     mayo
    1.79
    mayo
    1.70
     mayonnaise
    1.17
    onnaise
    1.09
    マヨ
    0.77
    onaise
    0.75
     майо
    0.71
    Activations Density 0.001%

    No Known Activations