© 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. 8703
    Prev
    Next
    INDEX
    Explanations

    words related to environmental topics and their implications

    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
    )]=
    -0.58
    ')}}"
    -0.57
     consecu
    -0.56
    ものが
    -0.55
     Contain
    -0.52
    phazard
    -0.52
    kreises
    -0.51
     Were
    -0.51
     Majefty
    -0.51
    setupUi
    -0.51
    POSITIVE LOGITS
     notwithstanding
    0.63
     here
    0.57
     during
    0.57
     aside
    0.56
    exitRule
    0.55
     hierzu
    0.54
    ंदीखरीदारी
    0.51
     certainly
    0.51
     throughout
    0.51
     daarvoor
    0.50
    Activations Density 0.583%

    No Known Activations