© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4218
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to criminal offenses and penalties

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

    Legal consequences and penalties

    np_acts-logits-general · gemini-2.0-flash

    legal penalties and punishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.75
     esternos
    -0.63
    jenost
    -0.52
    tisseur
    -0.49
     filtering
    -0.48
    arel
    -0.47
    principalTable
    -0.46
    contentLoaded
    -0.46
     Filtering
    -0.45
    houding
    -0.45
    POSITIVE LOGITS
     punishable
    1.01
     penalties
    0.93
     punished
    0.88
     punishment
    0.87
     consequences
    0.81
     punishments
    0.79
     penalty
    0.78
     Punishment
    0.78
     Penalties
    0.75
     punish
    0.73
    Activations Density 0.290%

    No Known Activations