© 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. 16-GEMMASCOPE-RES-16K
    11. 8736
    Prev
    Next
    INDEX
    Explanations

    concepts related to biochemical interactions and metabolic processes

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

    "delay" or "delayed"

    np_acts-logits-general · gemini-2.0-flash

    delayed arrival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.63
    isk
    -0.45
    ISK
    -0.44
    setupUi
    -0.42
    経歴
    -0.42
    bali
    -0.41
    Continued
    -0.41
     διά
    -0.41
     رح
    -0.40
    govina
    -0.40
    POSITIVE LOGITS
     delayed
    1.45
     delay
    1.32
     Delayed
    1.20
     delays
    1.19
    delayed
    1.15
    Delayed
    1.11
     DELAY
    1.11
     Delay
    1.10
     retraso
    1.09
     Delays
    1.06
    Activations Density 0.438%

    No Known Activations