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. 11-GEMMASCOPE-RES-16K
    6. 13618
    Prev
    Next
    INDEX
    Explanations

    references to societal change and reactions to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.59
    ício
    -0.49
    Spoljašnje
    -0.46
     pinta
    -0.44
     getStart
    -0.42
    γραφία
    -0.41
    انیا
    -0.40
    انجليز
    -0.40
     Collapse
    -0.39
     становника
    -0.39
    POSITIVE LOGITS
    ContentAsync
    0.72
    RTEE
    0.72
    oneofs
    0.67
     spirits
    0.65
    tagext
    0.65
     spirit
    0.63
     Réponses
    0.63
    twimg
    0.62
    protoimpl
    0.62
    kheim
    0.60
    Activations Density 0.084%

    No Known Activations