© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10034
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to crimes and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -1.02
    Билгалдахарш
    -0.88
    yntaxException
    -0.87
     EconPapers
    -0.84
     initComponents
    -0.83
    تقاوى
    -0.83
     iprot
    -0.82
    ChildScrollView
    -0.75
     }}"></
    -0.75
    PRNewswire
    -0.75
    POSITIVE LOGITS
     Griechen
    0.54
     képes
    0.51
     kepad
    0.46
     venuto
    0.45
     női
    0.44
    jenigen
    0.43
    .
    0.42
     interiores
    0.42
     Eintrag
    0.41
     the
    0.41
    Activations Density 2.782%

    No Known Activations