Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14810
    Prev
    Next
    INDEX
    Explanations

    themes related to Westerns and their associated tropes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arquitecto
    -0.34
     петербург
    -0.33
     Metropolitana
    -0.33
     tablette
    -0.30
    lotten
    -0.28
     ladrillo
    -0.28
     Kelurahan
    -0.28
     ЖК
    -0.28
     Gä
    -0.28
     bairro
    -0.28
    POSITIVE LOGITS
     cowboy
    1.41
     cowboys
    1.36
    cowboy
    1.20
     Cowboy
    1.16
     rodeo
    1.09
     ranchers
    1.09
     sheriff
    1.08
    Cowboy
    1.07
     rancher
    1.07
     Sheriff
    1.05
    Activations Density 0.453%

    No Known Activations