© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6183
    Prev
    Next
    INDEX
    Explanations

    instances of the word "address" and its variations, indicating discussions about issues that need to be resolved or responded to

    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
     joão
    -0.51
    pgterms
    -0.50
    Controllo
    -0.49
    Instruments
    -0.47
    ThroughAttribute
    -0.47
    principalTable
    -0.43
    UnsafeEnabled
    -0.43
    цездатний
    -0.41
    autoreleasepool
    -0.41
     increí
    -0.41
    POSITIVE LOGITS
     addressing
    1.19
     addressed
    1.11
     Addressing
    1.05
    Addressing
    1.01
    addressed
    1.00
     addresses
    0.96
    address
    0.89
     ADDRESS
    0.86
     Address
    0.84
     address
    0.82
    Activations Density 0.145%

    No Known Activations