© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 1503
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming, events, and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    方面的
    -0.37
    umbo
    -0.34
    elif
    -0.33
    +-+-
    -0.32
    quicks
    -0.32
    GOTREF
    -0.32
    +#+
    -0.32
    Ngh
    -0.32
    Ping
    -0.31
    Rip
    -0.31
    POSITIVE LOGITS
     itself
    1.32
     Itself
    1.00
    itself
    0.98
     itſelf
    0.82
    SharedCtor
    0.69
    本身
    0.67
     kendisi
    0.66
     entera
    0.61
    kesmas
    0.60
    及其
    0.59
    Activations Density 1.749%

    No Known Activations