© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to software development and data protocols

    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
    UrlResolution
    -0.55
    DebuggerStep
    -0.50
     Espanha
    -0.46
    fromnode
    -0.45
     ArrayAdapter
    -0.45
     tàn
    -0.44
    encodeWith
    -0.44
     useAppContext
    -0.44
    LLocation
    -0.44
     Riche
    -0.43
    POSITIVE LOGITS
    protobuf
    1.24
    protoc
    0.93
     protoimpl
    0.82
     protobuf
    0.74
    Protobuf
    0.73
    protoimpl
    0.72
    FieldDescriptor
    0.71
     jspb
    0.69
    CodedInputStream
    0.68
     Protobuf
    0.65
    Activations Density 0.421%

    No Known Activations