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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1669
    Prev
    Next
    INDEX
    Explanations

    references to the RabbitMQ library and related coding examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to message queue topics

    np_acts-logits-general · gemini-2.0-flash

    publishing to topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.60
     cipolla
    -0.57
    KommentareTeilen
    -0.55
    וויק
    -0.54
    ValueStyle
    -0.53
    BeginContext
    -0.51
     nawr
    -0.49
    usercontent
    -0.48
    PreferredItem
    -0.48
     Jurí
    -0.48
    POSITIVE LOGITS
     Topic
    0.96
    Topic
    0.96
     topic
    0.89
    topic
    0.86
     TOPIC
    0.82
    Topics
    0.79
     rabbit
    0.79
     Rabbit
    0.79
     topics
    0.77
    TOPIC
    0.76
    Activations Density 0.204%

    No Known Activations