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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24596
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to motions and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    motion filed and supported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.77
    themselves
    -0.74
     ourselves
    -0.71
     itself
    -0.69
     yourselves
    -0.68
     Itself
    -0.66
     Himself
    -0.65
    itself
    -0.65
     yourself
    -0.65
     herself
    -0.65
    POSITIVE LOGITS
     motion
    1.52
    motion
    1.27
     Motion
    1.23
    Motion
    1.22
     MOTION
    1.16
     seconded
    1.13
     motions
    1.11
    MOTION
    0.91
     Motions
    0.90
    secon
    0.88
    Activations Density 0.082%

    No Known Activations