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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 3453
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarity or comparison across subjects or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.65
    limus
    -0.57
    uot
    -0.56
     المتحدة
    -0.55
     iconLine
    -0.54
    ंदीखरीदारी
    -0.54
    uré
    -0.52
    באנגלית
    -0.52
    housie
    -0.51
    utilité
    -0.51
    POSITIVE LOGITS
     resultCode
    0.55
    WriteTagHelper
    0.52
     CreateTagHelper
    0.52
     <>",
    0.51
    ungguh
    0.51
    PerformLayout
    0.49
    PullParser
    0.49
     Cib
    0.47
    Personensuche
    0.47
    PARTMENT
    0.47
    Activations Density 0.742%

    No Known Activations