© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11801
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to chemical interactions and properties

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

    Scientific or technical processes

    np_acts-logits-general · gemini-2.0-flash

    chemical processes and their properties

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
     صوتيه
    -0.76
     betweenstory
    -0.74
    URLException
    -0.70
    fjspx
    -0.69
    abestanden
    -0.67
    thoscope
    -0.66
    __*/
    -0.64
    labus
    -0.61
     ProtoMessage
    -0.60
    othes
    -0.60
    POSITIVE LOGITS
     rate
    0.86
     phenomenon
    0.81
     process
    0.80
     phenomena
    0.79
     events
    0.77
     behaviour
    0.72
     rates
    0.71
     processes
    0.71
     behavior
    0.70
     capacity
    0.65
    Activations Density 1.560%

    No Known Activations