© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12094
    Prev
    Next
    INDEX
    Explanations

    references to annual events and gatherings

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

    ordinal numbers combined with the word "annual" (such as "4th annual", "20th annual").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muerto
    -0.43
     sorpresas
    -0.41
     flexibilidad
    -0.40
     vigencia
    -0.39
     autorización
    -0.37
     desplazamiento
    -0.37
     negociación
    -0.36
     publicidad
    -0.35
     vivienda
    -0.35
     corrupción
    -0.35
    POSITIVE LOGITS
     itſelf
    0.71
     Majefty
    0.69
     Conſ
    0.66
     ſind
    0.66
    MENAFN
    0.65
     Anſ
    0.65
     Smart
    0.63
     Reſ
    0.63
     myſelf
    0.63
     Monfieur
    0.63
    Activations Density 0.588%

    No Known Activations