© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9966
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to actions taken within a judicial context

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

    Follows the word "Agreed"

    np_acts-logits-general · gemini-2.0-flash

    actions leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olerance
    -0.56
    TagHelper
    -0.54
     Arquitectura
    -0.52
    исленность
    -0.52
    Mutability
    -0.50
     Gestión
    -0.49
    Stability
    -0.49
    Smell
    -0.49
    Termination
    -0.48
     tege
    -0.48
    POSITIVE LOGITS
     Made
    1.05
     Created
    0.98
     Presented
    0.97
     Held
    0.95
     Found
    0.93
     Offered
    0.92
     Received
    0.91
     Entered
    0.91
     Brought
    0.91
    Made
    0.91
    Activations Density 0.532%

    No Known Activations