© 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 EvalsExportsinterp-engineNEWAPI 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. 793
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to structural characteristics and their functions

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

    followed by "found," "seen," or "observed."

    np_acts-logits-general · gemini-2.0-flash

    found patterns and structures

    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
    principalTable
    -0.58
     jScrollPane
    -0.53
    ugier
    -0.51
    StoryboardSegue
    -0.51
     nisso
    -0.50
     auprès
    -0.49
     doInBackground
    -0.49
     дописавши
    -0.48
    penup
    -0.47
    didSet
    -0.47
    POSITIVE LOGITS
     found
    1.64
     seen
    1.58
    found
    1.44
     observed
    1.42
    Seen
    1.38
     encountered
    1.36
     Found
    1.36
     characteristic
    1.34
    seen
    1.31
    Found
    1.29
    Activations Density 0.974%

    No Known Activations