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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 7410
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining experiences and restaurant descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.82
     Picchu
    -0.77
     يتيمه
    -0.76
    MemoryWarning
    -0.75
    حياته
    -0.72
     dAtA
    -0.72
     '\\;'
    -0.71
     MonoBehaviour
    -0.71
    aarrggbb
    -0.68
    writeField
    -0.68
    POSITIVE LOGITS
     dining
    0.63
     seating
    0.60
     customers
    0.59
     clientèle
    0.58
    店内
    0.55
    店内は
    0.51
     staff
    0.51
     seats
    0.51
     seated
    0.49
     restaurant
    0.48
    Activations Density 0.093%

    No Known Activations