© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6627
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting the complexity and importance of community, personal connections, and identity

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

    followed by a comparison

    np_acts-logits-general · gemini-2.0-flash

    beyond or not only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.53
     nakalista
    -0.51
    TextWatcher
    -0.48
    uegos
    -0.47
     Sprague
    -0.43
     Trường
    -0.42
    tikai
    -0.42
    rowave
    -0.42
    tvguidetime
    -0.41
    viens
    -0.41
    POSITIVE LOGITS
     beyond
    1.64
    beyond
    1.50
    不仅仅
    1.41
    Beyond
    1.38
     Beyond
    1.34
     bukan
    1.33
     BEYOND
    1.23
     not
    1.16
    delà
    1.07
     Bukan
    1.06
    Activations Density 0.541%

    No Known Activations