© 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. 18-GEMMASCOPE-RES-16K
    11. 12831
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terms related to order or sequences

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

    Ordinal numbers following a variable name

    np_acts-logits-general · gemini-2.0-flash

    ordinal number suffixes (i-th, j-th)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.78
    ########.
    -0.61
     MainAxisSize
    -0.48
    Chapters
    -0.47
    StateList
    -0.47
     Chapters
    -0.46
     snippetHide
    -0.46
    δου
    -0.45
    วย
    -0.45
    Diwedd
    -0.44
    POSITIVE LOGITS
     fifth
    1.58
     fourth
    1.54
     sixth
    1.54
     third
    1.52
     seventh
    1.47
     eighth
    1.41
     ninth
    1.40
     tenth
    1.36
    fifth
    1.34
    third
    1.33
    Activations Density 0.368%

    No Known Activations