© 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. 22-GEMMASCOPE-RES-16K
    11. 3516
    Prev
    Next
    INDEX
    Explanations

    statistical and numerical data related to measurements and comparisons in scientific studies

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

    Preceding tokens before "respectively"

    np_acts-logits-general · gemini-2.0-flash

    separators followed by respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.81
     otomatig
    -0.70
     mergeFrom
    -0.66
     betweenstory
    -0.63
     flesta
    -0.63
     חיצוניים
    -0.58
    sprozess
    -0.57
    
    -0.57
    Benefit
    -0.55
    everything
    -0.55
    POSITIVE LOGITS
     respectively
    4.24
    respectively
    3.58
     respectivamente
    3.22
     respectivement
    2.75
     respective
    2.55
     rispet
    2.44
     соответственно
    2.43
     respec
    2.42
    respective
    1.96
     RESPECT
    1.83
    Activations Density 0.722%

    No Known Activations