© 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. 21-GEMMASCOPE-RES-16K
    11. 2550
    Prev
    Next
    INDEX
    Explanations

    terms related to re-evaluation and re-utilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.83
     définiti
    -0.72
    bootstrapcdn
    -0.71
    hésite
    -0.68
     olvidado
    -0.66
    เอง
    -0.64
    pisah
    -0.64
     Unterschied
    -0.64
     Wandel
    -0.63
    まま
    -0.61
    POSITIVE LOGITS
     re
    0.62
    AccessFile
    0.61
    gameserver
    0.53
    LOAT
    0.43
    wright
    0.42
    setAccessible
    0.42
     matric
    0.41
     насељу
    0.41
    app
    0.41
    herst
    0.41
    Activations Density 0.118%

    No Known Activations