© 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. 34-GEMMASCOPE-RES-16K
    11. 8062
    Prev
    Next
    INDEX
    Explanations

    legal arguments and references concerning court procedures and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confirmed
    -0.48
    kijken
    -0.47
     confirmó
    -0.46
     confirme
    -0.44
     confirmado
    -0.42
     confirms
    -0.42
     confirm
    -0.42
     confirmé
    -0.41
    नलिखित
    -0.41
     confirming
    -0.40
    POSITIVE LOGITS
     argument
    2.84
     arguments
    2.59
     argue
    2.42
     Argument
    2.34
     argued
    2.31
     arguing
    2.28
    argument
    2.27
     argumento
    2.25
     Arguments
    2.23
     argues
    2.11
    Activations Density 1.555%

    No Known Activations