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. 16-GEMMASCOPE-RES-16K
    6. 12915
    Prev
    Next
    INDEX
    Explanations

    phrases expressing faith and encouragement

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

    God or prayer

    np_acts-logits-general · gemini-2.0-flash

    god's gifts and timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.70
    RenderAtEndOf
    -0.66
     '-':
    -0.61
    BeginContext
    -0.54
     defStyle
    -0.54
     Kaka
    -0.53
     Shakspeare
    -0.52
    ->___
    -0.52
     Classification
    -0.52
     Confucius
    -0.52
    POSITIVE LOGITS
    enumi
    0.63
     AssemblyCompany
    0.60
     CreateTagHelper
    0.60
    EndInit
    0.57
    XmlIgnore
    0.53
     disambiguazione
    0.51
     McLaughlin
    0.48
     rechnen
    0.48
     rowspan
    0.47
    DebuggerNonUser
    0.47
    Activations Density 0.092%

    No Known Activations