© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6147
    Prev
    Next
    INDEX
    Explanations

    phrases related to online shopping and discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .(
    -0.56
     couche
    -0.48
    いた
    -0.47
    setName
    -0.47
     Poole
    -0.47
    ,(
    -0.47
    WireFormat
    -0.47
     yw
    -0.46
     theo
    -0.46
     فريبيس
    -0.45
    POSITIVE LOGITS
     itſelf
    0.88
    neſs
    0.84
    ſelves
    0.83
     Majefty
    0.83
     myſelf
    0.82
    ^(@)
    0.80
    ſelf
    0.80
     يتيمه
    0.76
     Efq
    0.76
    BeginInit
    0.76
    Activations Density 0.042%

    No Known Activations