© 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. 27-GEMMASCOPE-RES-16K
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    references to legal definitions and regulations concerning criminal offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.57
    KEYCODE
    -0.53
    ьаж
    -0.53
     ExecuteAsync
    -0.52
    pertino
    -0.51
    angeran
    -0.50
     nahilalakip
    -0.49
    Personendaten
    -0.49
     layak
    -0.48
    ysacchar
    -0.48
    POSITIVE LOGITS
     Gegenstände
    0.44
     cál
    0.34
     montón
    0.34
     exercice
    0.33
    ãng
    0.32
     ProtoMessage
    0.32
    ercizio
    0.31
     getObject
    0.30
     :-(
    0.30
     tertentu
    0.30
    Activations Density 0.586%

    No Known Activations