© 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. 33-GEMMASCOPE-RES-16K
    11. 6996
    Prev
    Next
    INDEX
    Explanations

    concepts related to equality and justice, particularly in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gering
    -0.36
    miri
    -0.36
    ceğine
    -0.36
    يكب
    -0.36
    Legături
    -0.35
    Portale
    -0.34
    illeurs
    -0.34
    webElementGuid
    -0.34
    orsch
    -0.34
     mlad
    -0.33
    POSITIVE LOGITS
    IntoConstraints
    0.67
    RTGC
    0.60
    GEBURTSDATUM
    0.59
    ValueStyle
    0.55
    CrossRef
    0.52
     Equ
    0.51
    (=)
    0.50
     Equal
    0.50
     footing
    0.49
    Архівовано
    0.49
    Activations Density 0.282%

    No Known Activations