© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to engineering and fluid dynamics

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

    Material/energy being supplied or returned

    np_acts-logits-general · gemini-2.0-flash

    flow of materials or energy

    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
    principalColumn
    -0.58
     ujednoznacz
    -0.58
    RegressionTest
    -0.57
    ainville
    -0.55
    JNIEnv
    -0.55
    hydrogenase
    -0.54
    Демографія
    -0.53
    IndentedString
    -0.52
     awakeFromNib
    -0.51
     Signalez
    -0.51
    POSITIVE LOGITS
     passing
    1.25
     coming
    1.18
     flowing
    1.04
    passing
    0.99
     flow
    0.99
     routed
    0.98
     arriving
    0.95
     entering
    0.95
     flows
    0.94
     Passing
    0.93
    Activations Density 0.925%

    No Known Activations