© 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. 8-GEMMASCOPE-RES-16K
    11. 1793
    Prev
    Next
    INDEX
    Explanations

    social media references and Internet culture elements

    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
     uſed
    -0.98
     myſelf
    -0.94
     raiſ
    -0.92
     diſt
    -0.92
     ſever
    -0.92
     iſt
    -0.91
    __":
    -0.91
     ſeveral
    -0.90
     poffible
    -0.90
    __':
    -0.89
    POSITIVE LOGITS
     memes
    0.61
    Derp
    0.57
     emoji
    0.55
     fucking
    0.53
    wut
    0.52
    зап
    0.52
    hella
    0.51
     aesthetic
    0.50
     G
    0.50
     meme
    0.49
    Activations Density 0.321%

    No Known Activations