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

    Neuronpedia

    Jacobian LensNEW
    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. 4742
    Prev
    Next
    INDEX
    Explanations

    elements related to visual representation and spatial arrangement

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

    Text below or after "bottom" or "lower"

    np_acts-logits-general · gemini-2.0-flash

    lower and bottom positions

    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
     maximization
    -0.55
    setMaximum
    -0.52
     رش
    -0.51
    maxsize
    -0.49
     maximizes
    -0.49
     незавершена
    -0.49
     maxSize
    -0.48
    maxim
    -0.48
    Maximum
    -0.48
     maximized
    -0.47
    POSITIVE LOGITS
     lower
    2.62
    lower
    2.31
     below
    2.29
     Lower
    2.23
    Lower
    2.22
     bottom
    2.22
     LOWER
    2.11
    below
    2.07
     Below
    2.03
     Bottom
    1.96
    Activations Density 0.793%

    No Known Activations