© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7926
    Prev
    Next
    INDEX
    Explanations

    phrases related to return policies and customer service

    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
    ⓧ
    -0.45
    maría
    -0.41
    psum
    -0.41
    committee
    -0.41
     suel
    -0.40
     recruiting
    -0.40
     pinulongan
    -0.40
    RoleName
    -0.40
     recruiters
    -0.40
     solteiro
    -0.39
    POSITIVE LOGITS
     refund
    1.31
     refunds
    1.21
     Refund
    1.09
     refunded
    1.05
     Refunds
    1.01
    refund
    1.00
    Refunds
    0.98
     REFUND
    0.94
    Refund
    0.92
    退款
    0.81
    Activations Density 0.204%

    No Known Activations