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. 25-GEMMASCOPE-RES-16K
    6. 4408
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases associated with shopping and consumer experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.67
     noDo
    -0.60
     Sympathy
    -0.54
    +:+
    -0.53
     Cemetery
    -0.52
     ejac
    -0.52
     kelahiran
    -0.51
    ativement
    -0.51
    twimg
    -0.51
    asteel
    -0.49
    POSITIVE LOGITS
     mall
    1.09
     malls
    0.99
    mall
    0.88
     Mall
    0.88
    Mall
    0.84
     department
    0.84
     shopping
    0.78
     MALL
    0.77
     متعلقه
    0.76
     Westfield
    0.74
    Activations Density 0.173%

    No Known Activations