© 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
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2194
    Prev
    Next
    INDEX
    Explanations

    references to capital and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.53
     auffi
    -0.42
    GEBURTS
    -0.41
     iprot
    -0.41
     Sensor
    -0.41
     Protobuf
    -0.40
    ❋
    -0.40
    XmlAccessorType
    -0.40
    ɵɵ
    -0.39
    Rüyada
    -0.39
    POSITIVE LOGITS
     capital
    1.73
    Capital
    1.56
     CAPITAL
    1.51
     Capital
    1.48
    capital
    1.48
    CAPITAL
    1.36
     capitale
    1.24
     capitals
    1.21
     capitalize
    1.09
     kapital
    1.07
    Activations Density 0.298%

    No Known Activations