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. 8-GEMMASCOPE-RES-16K
    6. 15280
    Prev
    Next
    INDEX
    Explanations

    phrases that ask about timing and conditions related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.85
    Autoritní
    -0.77
    WriteLiteral
    -0.69
     autorytatywna
    -0.68
    PyExc
    -0.66
    zugehen
    -0.64
    createStatement
    -0.63
    sprozess
    -0.61
    Tracce
    -0.61
     resourceCulture
    -0.59
    POSITIVE LOGITS
     kapan
    0.76
     cuándo
    0.69
    何时
    0.64
     times
    0.63
     anytime
    0.60
    testens
    0.59
    illoin
    0.59
     time
    0.59
     panahon
    0.59
     timetable
    0.57
    Activations Density 0.259%

    No Known Activations