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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13523
    Prev
    Next
    INDEX
    Explanations

    instances of the word "como," which means "how" or "like" in several languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.79
    twimg
    -0.71
    ccess
    -0.56
    INCREF
    -0.51
     Signalez
    -0.51
    jang
    -0.49
     تعدى
    -0.48
     Enjoy
    -0.47
    ivir
    -0.47
    ThroughAttribute
    -0.47
    POSITIVE LOGITS
     comme
    1.98
     como
    1.94
     як
    1.71
     jako
    1.67
    como
    1.67
     COMO
    1.65
    Como
    1.65
     как
    1.61
     kaip
    1.59
     Como
    1.58
    Activations Density 0.020%

    No Known Activations