© 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. 20-GEMMASCOPE-RES-131K
    11. 82367
    Prev
    Next
    INDEX
    Explanations

    terminology related to incarceration and inmate management

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

    penal system, inmates, jail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.42
    期刊论文
    -0.37
     movilidad
    -0.35
     tebal
    -0.35
     resistência
    -0.35
     utafitiHapana
    -0.34
    zdě
    -0.34
     saiba
    -0.33
    richTextPanel
    -0.33
     يتيمه
    -0.33
    POSITIVE LOGITS
     ModelExpression
    0.60
    ContentAsync
    0.57
     مشين
    0.56
    IndentedString
    0.52
    webElementGuid
    0.50
    testify
    0.48
    WebServlet
    0.47
     patients
    0.47
    قایناق‌لار
    0.46
     '\\;'
    0.46
    Activations Density 0.022%

    No Known Activations