© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12510
    Prev
    Next
    INDEX
    Explanations

    discussions about economic disparities and health issues impacting specific demographic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     例
    -0.32
     centred
    -0.31
     большого
    -0.30
     colourful
    -0.29
    曖昧さ回避
    -0.29
     disini
    -0.29
    ๆ
    -0.28
     grossen
    -0.28
     tập
    -0.28
     olvas
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.83
    msgTypes
    0.74
    sizeCache
    0.69
    writeFieldEnd
    0.67
    يكب
    0.66
    ngdoc
    0.66
     Normdatei
    0.64
     AssemblyCompany
    0.63
    tagHelperRunner
    0.63
     protoimpl
    0.63
    Activations Density 0.180%

    No Known Activations