© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50364
    Prev
    Next
    INDEX
    Explanations

    references to "ju" or related terms, likely focusing on topics involving judges or judicial processes

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

    june, july

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שלו
    -0.45
     Nusantara
    -0.42
    ts
    -0.40
     Estación
    -0.40
    texttt
    -0.40
     vectorielles
    -0.40
     supporting
    -0.39
     Équipe
    -0.38
     parís
    -0.38
     Pacífico
    -0.37
    POSITIVE LOGITS
     Ju
    2.39
    Ju
    2.28
     ju
    2.19
    ju
    1.89
     JU
    1.87
    JU
    1.75
     Juju
    1.49
    Juice
    1.19
     Juice
    1.13
    juice
    1.11
    Activations Density 0.007%

    No Known Activations