© 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. 5859
    Prev
    Next
    INDEX
    Explanations

    references to relative pricing and locations in different cities

    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
    cestershire
    -0.31
    getattr
    -0.29
    atorship
    -0.28
    textit
    -0.26
    glTex
    -0.26
    NHS
    -0.26
     Landkreis
    -0.25
    超
    -0.25
    atsch
    -0.25
    SRC
    -0.25
    POSITIVE LOGITS
     London
    1.80
     Tokyo
    1.72
     Toronto
    1.72
     Bangkok
    1.67
     Mumbai
    1.66
     Jakarta
    1.64
     Dublin
    1.59
     Seoul
    1.59
     Chicago
    1.59
     Manila
    1.58
    Activations Density 1.078%

    No Known Activations