© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12726
    Prev
    Next
    INDEX
    Explanations

    terms related to inflammation and cellular signaling pathways

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

    Tokens followed by Greek letters

    np_acts-logits-general · gemini-2.0-flash

    PPAR, alpha, gamma, and factors

    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
    usercontent
    -0.47
    ͝
    -0.45
    ler
    -0.45
    ArgumentParser
    -0.42
     awakeFromNib
    -0.42
     uș
    -0.42
    rob
    -0.40
     man
    -0.40
     Quốc
    -0.40
    ísticas
    -0.39
    POSITIVE LOGITS
     delta
    1.00
     beta
    0.96
     Delta
    0.92
     alpha
    0.90
     DELTA
    0.89
     gamma
    0.88
     Beta
    0.86
     Lambda
    0.83
     lambda
    0.82
     للمعارف
    0.81
    Activations Density 3.359%

    No Known Activations