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

    Neuronpedia

    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. 117
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structures related to expressions involving braces and sets

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

    LaTeX commands (mathrm, Tr, Vol)

    np_acts-logits-general · gemini-2.0-flash

    $\mathrm{Tr}$

    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
     distanciation
    -0.80
    OLOGIES
    -0.71
     ever
    -0.65
    InjectAttribute
    -0.64
    $=\
    -0.62
    </blockquote>
    -0.59
     الاطلاع
    -0.59
    makeConstraints
    -0.58
    Gambas
    -0.57
    Coordenadas
    -0.57
    POSITIVE LOGITS
    :'/
    0.71
    </u>
    0.70
    (‘
    0.67
     _('
    0.66
     regioni
    0.66
     fédé
    0.64
    ={`/
    0.63
     portátiles
    0.63
     ogóle
    0.62
     Italij
    0.61
    Activations Density 0.264%

    No Known Activations