© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3300
    Prev
    Next
    INDEX
    Explanations

    terms related to Nepal and its cultural or geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.63
    الدراسه
    -0.54
    期刊论文
    -0.51
    InputBorder
    -0.50
     Exactos
    -0.49
    */),
    -0.49
    ConstraintMaker
    -0.48
    tagHelperRunner
    -0.48
     <>",
    -0.48
    transQ
    -0.48
    POSITIVE LOGITS
     Nepal
    0.73
    mandu
    0.66
    Nepal
    0.65
     Kathmandu
    0.59
     Nepali
    0.52
    netbeans
    0.51
     nahilalakip
    0.47
     Bolivia
    0.46
     Nebraska
    0.44
     geologist
    0.44
    Activations Density 0.152%

    No Known Activations