© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 457
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to cryptocurrency and market dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.78
     cherchés
    -0.69
    ništ
    -0.63
    ollectionView
    -0.62
     anglès
    -0.59
    mêmes
    -0.58
    LEncoder
    -0.54
     архивлан
    -0.54
     tanong
    -0.54
    ItemBackground
    -0.52
    POSITIVE LOGITS
     bicic
    0.55
    alak
    0.55
     rospy
    0.54
    جوايز
    0.54
    BASEPATH
    0.54
    SupportActionBar
    0.52
     frères
    0.52
    )$/,
    0.52
     médec
    0.51
     poveznice
    0.51
    Activations Density 0.428%

    No Known Activations