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. 5-GEMMASCOPE-RES-16K
    6. 1460
    Prev
    Next
    INDEX
    Explanations

    phrases or terms commonly related to the concept of time, particularly the word "after"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.94
     AttributeSet
    -0.84
     Jefus
    -0.79
    MessageTagHelper
    -0.78
     Theſe
    -0.78
    mặt
    -0.75
     Shakspeare
    -0.74
     myſelf
    -0.74
    itecture
    -0.74
     himſelf
    -0.73
    POSITIVE LOGITS
     after
    2.07
    after
    1.90
     After
    1.87
    After
    1.84
     dopo
    1.63
     após
    1.59
     после
    1.58
     AFTER
    1.55
    AFTER
    1.54
     après
    1.51
    Activations Density 0.220%

    No Known Activations