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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13613
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to criminal cases and legal proceedings

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

    specific legal and formal case citations or references within documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.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
     cioè
    -0.61
    antaranya
    -0.59
     namely
    -0.58
    IntoConstraints
    -0.57
     disambiguazione
    -0.56
     Namely
    -0.55
    namely
    -0.54
     yaitu
    -0.54
    featureID
    -0.52
     notamment
    -0.51
    POSITIVE LOGITS
     like
    1.70
     подоб
    1.17
     similar
    1.07
     seperti
    1.04
     Like
    1.02
     LIKE
    1.02
    like
    0.98
     such
    0.95
    のような
    0.94
    Like
    0.93
    Activations Density 0.431%

    No Known Activations