© 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. 2-GEMMASCOPE-RES-16K
    11. 3991
    Prev
    Next
    INDEX
    Explanations

    references to air and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.86
    LETED
    -0.85
    expandindo
    -0.76
    期刊论文
    -0.74
    StoreMessageInfo
    -0.73
    chenken
    -0.71
     للاسماء
    -0.70
    RegressionTest
    -0.69
     Spéc
    -0.69
    Personensuche
    -0.68
    POSITIVE LOGITS
     air
    3.92
    air
    3.35
     Air
    3.22
    Air
    3.19
     AIR
    2.99
    AIR
    2.78
     airs
    2.34
     aire
    2.24
     Luft
    2.06
     luft
    2.04
    Activations Density 0.067%

    No Known Activations