© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and format elements used in equations and alignments

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

    LaTeX "align" environments

    np_acts-logits-general · gemini-2.0-flash

    LaTeX align environments

    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
    endpush
    -0.81
     pleaſure
    -0.73
     purpoſe
    -0.72
    Geplaatst
    -0.71
     itſelf
    -0.70
     ſtate
    -0.70
     fubject
    -0.68
     fhort
    -0.67
    InitVars
    -0.65
     Theſe
    -0.65
    POSITIVE LOGITS
     Réponses
    0.50
    ConstraintMaker
    0.46
    LABEL
    0.46
    CloseOperation
    0.46
    jabi
    0.45
    olit
    0.45
    Personensuche
    0.43
    SqlClient
    0.43
    eqnarray
    0.42
     label
    0.42
    Activations Density 0.492%

    No Known Activations