© 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. 2-GEMMASCOPE-RES-16K
    11. 2167
    Prev
    Next
    INDEX
    Explanations

    legal motions and procedural terms in court documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.63
    zaamheid
    -0.44
     plaat
    -0.42
     pinulongan
    -0.39
     przys
    -0.38
     ambientale
    -0.37
    COMPAT
    -0.36
    Elő
    -0.35
    odos
    -0.35
    WriteTagHelper
    -0.35
    POSITIVE LOGITS
     motion
    0.74
    motion
    0.71
     Motion
    0.70
    Motion
    0.70
     MOTION
    0.68
     dipped
    0.65
     dip
    0.65
     dips
    0.64
     hop
    0.63
    badlogic
    0.58
    Activations Density 0.583%

    No Known Activations