© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12142
    Prev
    Next
    INDEX
    Explanations

    references to monetary values or currency-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſont
    -0.58
     ſind
    -0.58
     externi
    -0.56
    klere
    -0.55
    quence
    -0.54
     ​
    -0.54
     ◄
    -0.53
    archive
    -0.52
    ANDUM
    -0.52
    odeon
    -0.51
    POSITIVE LOGITS
     $
    1.31
    $
    1.30
     \$
    1.00
    //$
    0.88
     '$
    0.87
    /$
    0.82
     £
    0.82
    ='$
    0.81
     $\$
    0.80
    ','$
    0.79
    Activations Density 0.834%

    No Known Activations